security: supply chain hardening — CI pinning, dep pinning, and code fixes (#9801)

CI/CD Hardening:
- Pin all 12 GitHub Actions to full commit SHAs (was mutable @vN tags)
- Add explicit permissions: {contents: read} to 4 workflows
- Pin CI pip installs to exact versions (pyyaml==6.0.2, httpx==0.28.1)
- Extend supply-chain-audit.yml to scan workflow, Dockerfile, dependency
  manifest, and Actions version changes

Dependency Pinning:
- Pin git-based Python deps to commit SHAs (atroposlib, tinker, yc-bench)
- Pin WhatsApp Baileys from mutable branch to commit SHA

Tool Registry:
- Reject tool name shadowing from different tool families (plugins/MCP
  cannot overwrite built-in tools). MCP-to-MCP overwrites still allowed.

MCP Security:
- Add tool description content scanning for prompt injection patterns
- Log detailed change diff on dynamic tool refresh at WARNING level

Skill Manager:
- Fix dangerous verdict bug: agent-created skills with dangerous
  findings were silently allowed (ask->None->allow). Now blocked.

.github/workflows/contributor-check.yml

@@ -9,11 +9,14 @@ on:
       - '**/*.py'
       - '.github/workflows/contributor-check.yml'
 
+permissions:
+  contents: read
+
 jobs:
   check-attribution:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
         with:
           fetch-depth: 0  # Full history needed for git log
 

.github/workflows/deploy-site.yml

@@ -28,20 +28,20 @@ jobs:
       name: github-pages
       url: ${{ steps.deploy.outputs.page_url }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
 
-      - uses: actions/setup-node@v4
+      - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020  # v4
         with:
           node-version: 20
           cache: npm
           cache-dependency-path: website/package-lock.json
 
-      - uses: actions/setup-python@v5
+      - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065  # v5
         with:
           python-version: '3.11'
 
       - name: Install PyYAML for skill extraction
-        run: pip install pyyaml httpx
+        run: pip install pyyaml==6.0.2 httpx==0.28.1
 
       - name: Extract skill metadata for dashboard
         run: python3 website/scripts/extract-skills.py
@@ -73,10 +73,10 @@ jobs:
           echo "hermes-agent.nousresearch.com" > _site/CNAME
 
       - name: Upload artifact
-        uses: actions/upload-pages-artifact@v3
+        uses: actions/upload-pages-artifact@56afc609e74202658d3ffba0e8f6dda462b719fa  # v3
         with:
           path: _site
 
       - name: Deploy to GitHub Pages
         id: deploy
-        uses: actions/deploy-pages@v4
+        uses: actions/deploy-pages@d6db90164ac5ed86f2b6aed7e0febac5b3c0c03e  # v4

.github/workflows/docker-publish.yml

@@ -23,21 +23,21 @@ jobs:
     timeout-minutes: 60
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
         with:
           submodules: recursive
 
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
+        uses: docker/setup-qemu-action@c7c53464625b32c7a7e944ae62b3e17d2b600130  # v3
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f  # v3
 
       # Build amd64 only so we can `load` the image for smoke testing.
       # `load: true` cannot export a multi-arch manifest to the local daemon.
       # The multi-arch build follows on push to main / release.
       - name: Build image (amd64, smoke test)
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8  # v6
         with:
           context: .
           file: Dockerfile
@@ -56,14 +56,14 @@ jobs:
 
       - name: Log in to Docker Hub
         if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'
-        uses: docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9  # v3
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Push multi-arch image (main branch)
         if: github.event_name == 'push' && github.ref == 'refs/heads/main'
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8  # v6
         with:
           context: .
           file: Dockerfile
@@ -75,7 +75,7 @@ jobs:
 
       - name: Push multi-arch image (release)
         if: github.event_name == 'release'
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8  # v6
         with:
           context: .
           file: Dockerfile

.github/workflows/docs-site-checks.yml

@@ -7,13 +7,16 @@ on:
       - '.github/workflows/docs-site-checks.yml'
   workflow_dispatch:
 
+permissions:
+  contents: read
+
 jobs:
   docs-site-checks:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
 
-      - uses: actions/setup-node@v4
+      - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020  # v4
         with:
           node-version: 20
           cache: npm
@@ -23,7 +26,7 @@ jobs:
         run: npm ci
         working-directory: website
 
-      - uses: actions/setup-python@v5
+      - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065  # v5
         with:
           python-version: '3.11'
 

.github/workflows/nix.yml

@@ -14,6 +14,9 @@ on:
       - 'run_agent.py'
       - 'acp_adapter/**'
 
+permissions:
+  contents: read
+
 concurrency:
   group: nix-${{ github.ref }}
   cancel-in-progress: true
@@ -26,7 +29,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     timeout-minutes: 30
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
       - uses: DeterminateSystems/nix-installer-action@ef8a148080ab6020fd15196c2084a2eea5ff2d25  # v22
       - uses: DeterminateSystems/magic-nix-cache-action@565684385bcd71bad329742eefe8d12f2e765b39  # v13
       - name: Check flake

.github/workflows/skills-index.yml

@@ -20,14 +20,14 @@ jobs:
     if: github.repository == 'NousResearch/hermes-agent'
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
 
-      - uses: actions/setup-python@v5
+      - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065  # v5
         with:
           python-version: '3.11'
 
       - name: Install dependencies
-        run: pip install httpx pyyaml
+        run: pip install httpx==0.28.1 pyyaml==6.0.2
 
       - name: Build skills index
         env:
@@ -35,7 +35,7 @@ jobs:
         run: python scripts/build_skills_index.py
 
       - name: Upload index artifact
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02  # v4
         with:
           name: skills-index
           path: website/static/api/skills-index.json
@@ -53,25 +53,25 @@ jobs:
     # Only deploy on schedule or manual trigger (not on every push to the script)
     if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
 
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093  # v4
         with:
           name: skills-index
           path: website/static/api/
 
-      - uses: actions/setup-node@v4
+      - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020  # v4
         with:
           node-version: 20
           cache: npm
           cache-dependency-path: website/package-lock.json
 
-      - uses: actions/setup-python@v5
+      - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065  # v5
         with:
           python-version: '3.11'
 
       - name: Install PyYAML for skill extraction
-        run: pip install pyyaml
+        run: pip install pyyaml==6.0.2
 
       - name: Extract skill metadata for dashboard
         run: python3 website/scripts/extract-skills.py
@@ -92,10 +92,10 @@ jobs:
           echo "hermes-agent.nousresearch.com" > _site/CNAME
 
       - name: Upload artifact
-        uses: actions/upload-pages-artifact@v3
+        uses: actions/upload-pages-artifact@56afc609e74202658d3ffba0e8f6dda462b719fa  # v3
         with:
           path: _site
 
       - name: Deploy to GitHub Pages
         id: deploy
-        uses: actions/deploy-pages@v4
+        uses: actions/deploy-pages@d6db90164ac5ed86f2b6aed7e0febac5b3c0c03e  # v4

.github/workflows/supply-chain-audit.yml

@@ -14,7 +14,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
         with:
           fetch-depth: 0
 
@@ -149,6 +149,62 @@ jobs:
           "
           fi
 
+          # --- CI/CD workflow files modified ---
+          WORKFLOW_HITS=$(git diff --name-only "$BASE".."$HEAD" | grep -E '\.github/workflows/.*\.ya?ml$' || true)
+          if [ -n "$WORKFLOW_HITS" ]; then
+            FINDINGS="${FINDINGS}
+          ### ⚠️ WARNING: CI/CD workflow files modified
+          Changes to workflow files can alter build pipelines, inject steps, or modify permissions. Verify no unauthorized actions or secrets access were added.
+
+          **Files:**
+          \`\`\`
+          ${WORKFLOW_HITS}
+          \`\`\`
+          "
+          fi
+
+          # --- Dockerfile / container build files modified ---
+          DOCKER_HITS=$(git diff --name-only "$BASE".."$HEAD" | grep -iE '(Dockerfile|\.dockerignore|docker-compose)' || true)
+          if [ -n "$DOCKER_HITS" ]; then
+            FINDINGS="${FINDINGS}
+          ### ⚠️ WARNING: Container build files modified
+          Changes to Dockerfiles or compose files can alter base images, add build steps, or expose ports. Verify base image pins and build commands.
+
+          **Files:**
+          \`\`\`
+          ${DOCKER_HITS}
+          \`\`\`
+          "
+          fi
+
+          # --- Dependency manifest files modified ---
+          DEP_HITS=$(git diff --name-only "$BASE".."$HEAD" | grep -E '(pyproject\.toml|requirements.*\.txt|package\.json|Gemfile|go\.mod|Cargo\.toml)$' || true)
+          if [ -n "$DEP_HITS" ]; then
+            FINDINGS="${FINDINGS}
+          ### ⚠️ WARNING: Dependency manifest files modified
+          Changes to dependency files can introduce new packages or change version pins. Verify all dependency changes are intentional and from trusted sources.
+
+          **Files:**
+          \`\`\`
+          ${DEP_HITS}
+          \`\`\`
+          "
+          fi
+
+          # --- GitHub Actions version unpinning (mutable tags instead of SHAs) ---
+          ACTIONS_UNPIN=$(echo "$DIFF" | grep -n '^\+' | grep 'uses:' | grep -v '#' | grep -E '@v[0-9]' | head -10 || true)
+          if [ -n "$ACTIONS_UNPIN" ]; then
+            FINDINGS="${FINDINGS}
+          ### ⚠️ WARNING: GitHub Actions with mutable version tags
+          Actions should be pinned to full commit SHAs (not \`@v4\`, \`@v5\`). Mutable tags can be retargeted silently if a maintainer account is compromised.
+
+          **Matches:**
+          \`\`\`
+          ${ACTIONS_UNPIN}
+          \`\`\`
+          "
+          fi
+
           # --- Output results ---
           if [ -n "$FINDINGS" ]; then
             echo "found=true" >> "$GITHUB_OUTPUT"

.github/workflows/tests.yml

@@ -6,6 +6,9 @@ on:
   pull_request:
     branches: [main]
 
+permissions:
+  contents: read
+
 # Cancel in-progress runs for the same PR/branch
 concurrency:
   group: tests-${{ github.ref }}
@@ -17,13 +20,13 @@ jobs:
     timeout-minutes: 10
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
 
       - name: Install system dependencies
         run: sudo apt-get update && sudo apt-get install -y ripgrep
 
       - name: Install uv
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@d4b2f3b6ecc6e67c4457f6d3e41ec42d3d0fcb86  # v5
 
       - name: Set up Python 3.11
         run: uv python install 3.11
@@ -49,10 +52,10 @@ jobs:
     timeout-minutes: 10
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
 
       - name: Install uv
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@d4b2f3b6ecc6e67c4457f6d3e41ec42d3d0fcb86  # v5
 
       - name: Set up Python 3.11
         run: uv python install 3.11

pyproject.toml

@@ -78,13 +78,13 @@ dingtalk = ["dingtalk-stream>=0.1.0,<1"]
 feishu = ["lark-oapi>=1.5.3,<2"]
 web = ["fastapi>=0.104.0,<1", "uvicorn[standard]>=0.24.0,<1"]
 rl = [
-  "atroposlib @ git+https://github.com/NousResearch/atropos.git",
+  "atroposlib @ git+https://github.com/NousResearch/atropos.git@c20c85256e5a45ad31edf8b7276e9c5ee1995a30",
-  "tinker @ git+https://github.com/thinking-machines-lab/tinker.git",
+  "tinker @ git+https://github.com/thinking-machines-lab/tinker.git@30517b667f18a3dfb7ef33fb56cf686d5820ba2b",
   "fastapi>=0.104.0,<1",
   "uvicorn[standard]>=0.24.0,<1",
   "wandb>=0.15.0,<1",
 ]
-yc-bench = ["yc-bench @ git+https://github.com/collinear-ai/yc-bench.git ; python_version >= '3.12'"]
+yc-bench = ["yc-bench @ git+https://github.com/collinear-ai/yc-bench.git@bfb0c88062450f46341bd9a5298903fc2e952a5c ; python_version >= '3.12'"]
 all = [
   "hermes-agent[modal]",
   "hermes-agent[daytona]",

scripts/whatsapp-bridge/package.json

@@ -8,7 +8,7 @@
     "start": "node bridge.js"
   },
   "dependencies": {
-    "@whiskeysockets/baileys": "WhiskeySockets/Baileys#fix/abprops-abt-fetch",
+    "@whiskeysockets/baileys": "WhiskeySockets/Baileys#01047debd81beb20da7b7779b08edcb06aa03770",
     "express": "^4.21.0",
     "qrcode-terminal": "^0.12.0",
     "pino": "^9.0.0"

tests/tools/test_mcp_tool.py

@@ -2837,7 +2837,7 @@ class TestRegistryCollisionWarning:
     """registry.register() warns when a tool name is overwritten by a different toolset."""
 
     def test_overwrite_different_toolset_logs_warning(self, caplog):
-        """Overwriting a tool from a different toolset emits a warning."""
+        """Overwriting a tool from a different toolset is REJECTED with an error."""
         from tools.registry import ToolRegistry
         import logging
 
@@ -2847,11 +2847,13 @@ class TestRegistryCollisionWarning:
 
         reg.register(name="my_tool", toolset="builtin", schema=schema, handler=handler)
 
-        with caplog.at_level(logging.WARNING, logger="tools.registry"):
+        with caplog.at_level(logging.ERROR, logger="tools.registry"):
             reg.register(name="my_tool", toolset="mcp-ext", schema=schema, handler=handler)
 
-        assert any("collision" in r.message.lower() for r in caplog.records)
+        assert any("rejected" in r.message.lower() for r in caplog.records)
         assert any("builtin" in r.message and "mcp-ext" in r.message for r in caplog.records)
+        # The original tool should still be from 'builtin', not overwritten
+        assert reg.get_toolset_for_tool("my_tool") == "builtin"
 
     def test_overwrite_same_toolset_no_warning(self, caplog):
         """Re-registering within the same toolset is silent (e.g. reconnect)."""

tools/mcp_tool.py

@@ -219,6 +219,58 @@ def _sanitize_error(text: str) -> str:
     return _CREDENTIAL_PATTERN.sub("[REDACTED]", text)
 
 
+# ---------------------------------------------------------------------------
+# MCP tool description content scanning
+# ---------------------------------------------------------------------------
+
+# Patterns that indicate potential prompt injection in MCP tool descriptions.
+# These are WARNING-level — we log but don't block, since false positives
+# would break legitimate MCP servers.
+_MCP_INJECTION_PATTERNS = [
+    (re.compile(r"ignore\s+(all\s+)?previous\s+instructions", re.I),
+     "prompt override attempt ('ignore previous instructions')"),
+    (re.compile(r"you\s+are\s+now\s+a", re.I),
+     "identity override attempt ('you are now a...')"),
+    (re.compile(r"your\s+new\s+(task|role|instructions?)\s+(is|are)", re.I),
+     "task override attempt"),
+    (re.compile(r"system\s*:\s*", re.I),
+     "system prompt injection attempt"),
+    (re.compile(r"<\s*(system|human|assistant)\s*>", re.I),
+     "role tag injection attempt"),
+    (re.compile(r"do\s+not\s+(tell|inform|mention|reveal)", re.I),
+     "concealment instruction"),
+    (re.compile(r"(curl|wget|fetch)\s+https?://", re.I),
+     "network command in description"),
+    (re.compile(r"base64\.(b64decode|decodebytes)", re.I),
+     "base64 decode reference"),
+    (re.compile(r"exec\s*\(|eval\s*\(", re.I),
+     "code execution reference"),
+    (re.compile(r"import\s+(subprocess|os|shutil|socket)", re.I),
+     "dangerous import reference"),
+]
+
+
+def _scan_mcp_description(server_name: str, tool_name: str, description: str) -> List[str]:
+    """Scan an MCP tool description for prompt injection patterns.
+
+    Returns a list of finding strings (empty = clean).
+    """
+    findings = []
+    if not description:
+        return findings
+    for pattern, reason in _MCP_INJECTION_PATTERNS:
+        if pattern.search(description):
+            findings.append(reason)
+    if findings:
+        logger.warning(
+            "MCP server '%s' tool '%s': suspicious description content — %s. "
+            "Description: %.200s",
+            server_name, tool_name, "; ".join(findings),
+            description,
+        )
+    return findings
+
+
 def _prepend_path(env: dict, directory: str) -> dict:
     """Prepend *directory* to env PATH if it is not already present."""
     updated = dict(env or {})
@@ -798,6 +850,9 @@ class MCPServerTask:
         from toolsets import TOOLSETS
 
         async with self._refresh_lock:
+            # Capture old tool names for change diff
+            old_tool_names = set(self._registered_tool_names)
+
             # 1. Fetch current tool list from server
             tools_result = await self.session.list_tools()
             new_mcp_tools = tools_result.tools if hasattr(tools_result, "tools") else []
@@ -817,10 +872,26 @@ class MCPServerTask:
                 self.name, self, self._config
             )
 
-            logger.info(
+            # 5. Log what changed (user-visible notification)
-                "MCP server '%s': dynamically refreshed %d tool(s)",
+            new_tool_names = set(self._registered_tool_names)
-                self.name, len(self._registered_tool_names),
+            added = new_tool_names - old_tool_names
-            )
+            removed = old_tool_names - new_tool_names
+            changes = []
+            if added:
+                changes.append(f"added: {', '.join(sorted(added))}")
+            if removed:
+                changes.append(f"removed: {', '.join(sorted(removed))}")
+            if changes:
+                logger.warning(
+                    "MCP server '%s': tools changed dynamically — %s. "
+                    "Verify these changes are expected.",
+                    self.name, "; ".join(changes),
+                )
+            else:
+                logger.info(
+                    "MCP server '%s': dynamically refreshed %d tool(s) (no changes)",
+                    self.name, len(self._registered_tool_names),
+                )
 
     async def _run_stdio(self, config: dict):
         """Run the server using stdio transport."""
@@ -1838,6 +1909,10 @@ def _register_server_tools(name: str, server: MCPServerTask, config: dict) -> Li
         if not _should_register(mcp_tool.name):
             logger.debug("MCP server '%s': skipping tool '%s' (filtered by config)", name, mcp_tool.name)
             continue
+
+        # Scan tool description for prompt injection patterns
+        _scan_mcp_description(name, mcp_tool.name, mcp_tool.description or "")
+
         schema = _convert_mcp_schema(name, mcp_tool)
         tool_name_prefixed = schema["name"]
 

tools/registry.py

@@ -117,11 +117,27 @@ class ToolRegistry:
         with self._lock:
             existing = self._tools.get(name)
             if existing and existing.toolset != toolset:
-                logger.warning(
+                # Allow MCP-to-MCP overwrites (legitimate: server refresh,
-                    "Tool name collision: '%s' (toolset '%s') is being "
+                # or two MCP servers with overlapping tool names).
-                    "overwritten by toolset '%s'",
+                both_mcp = (
-                    name, existing.toolset, toolset,
+                    existing.toolset.startswith("mcp-")
+                    and toolset.startswith("mcp-")
                 )
+                if both_mcp:
+                    logger.debug(
+                        "Tool '%s': MCP toolset '%s' overwriting MCP toolset '%s'",
+                        name, toolset, existing.toolset,
+                    )
+                else:
+                    # Reject shadowing — prevent plugins/MCP from overwriting
+                    # built-in tools or vice versa.
+                    logger.error(
+                        "Tool registration REJECTED: '%s' (toolset '%s') would "
+                        "shadow existing tool from toolset '%s'. Deregister the "
+                        "existing tool first if this is intentional.",
+                        name, toolset, existing.toolset,
+                    )
+                    return
             self._tools[name] = ToolEntry(
                 name=name,
                 toolset=toolset,

tools/skill_manager_tool.py

@@ -64,11 +64,11 @@ def _security_scan_skill(skill_dir: Path) -> Optional[str]:
             report = format_scan_report(result)
             return f"Security scan blocked this skill ({reason}):\n{report}"
         if allowed is None:
-            # "ask" — allow but include the warning so the user sees the findings
+            # "ask" verdict — for agent-created skills this means dangerous
+            # findings were detected.  Block the skill and include the report.
             report = format_scan_report(result)
-            logger.warning("Agent-created skill has security findings: %s", reason)
+            logger.warning("Agent-created skill blocked (dangerous findings): %s", reason)
-            # Don't block — return None to allow, but log the warning
+            return f"Security scan blocked this skill ({reason}):\n{report}"
-            return None
     except Exception as e:
         logger.warning("Security scan failed for %s: %s", skill_dir, e, exc_info=True)
     return None