mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-30 06:41:51 +00:00
249534e472
New opt-in plugin that scans the content passed to write_file / patch /
skill_manage for 25 known-dangerous code patterns — pickle.load,
yaml.load, eval(, os.system, subprocess(shell=True), child_process.exec,
dangerouslySetInnerHTML, innerHTML/outerHTML/document.write/
insertAdjacentHTML, crypto.createCipher (no IV), AES ECB,
TLS verification disabled, XXE-prone xml.etree/minidom parsers,
<script src=//...> without SRI, torch.load without weights_only=True,
GitHub Actions ${{ github.event.* }} injection — and appends a
"Security guidance" warning block to the tool result via the
transform_tool_result hook.
Default behaviour is non-blocking: the file is written and the warning
rides back to the model in the next turn so it can self-correct or
document why the construct is safe. SECURITY_GUIDANCE_BLOCK=1 upgrades
to refusing the write entirely; SECURITY_GUIDANCE_DISABLE=1 is the
kill switch.
Pattern data (patterns.py) is a verbatim Apache-2.0 fork of
Anthropic's claude-plugins-official/plugins/security-guidance/hooks/
patterns.py at commit 0bde168 (2026-05-26). LICENSE and NOTICE
preserve attribution. The Hermes-side plugin glue (__init__.py,
plugin.yaml, README.md, tests) is original work.
Plugin is opt-in like all bundled plugins:
hermes plugins enable security-guidance
Inspired by https://x.com/ClaudeDevs/status/1927108527247... — Anthropic
shipped this as their security-guidance plugin for Claude Code on
2026-05-26 with a measured 30-40% reduction in security-related PR
comments on internal rollout.
What's NOT ported (deferred):
* Layer 2 (LLM diff review on turn end) — would route through main
model by default on Hermes, real money on reasoning models. A
follow-up can wire it to a cheap aux model with explicit opt-in.
* Layer 3 (agentic commit-time review) — agent can run this on
demand via delegate_task today.
* .hermes/security-guidance.md project-rules file — only used by
layers 2/3 upstream.
7 lines
626 B
YAML
7 lines
626 B
YAML
name: security-guidance
|
|
version: "0.1.0"
|
|
description: "Append security warnings to file-write tool results when the new content contains known-dangerous patterns (pickle.load, yaml.load, eval(, os.system, dangerouslySetInnerHTML, verify=False, ECB, XXE, GitHub Actions injection, ...). 25 regex/substring rules forked from Anthropic's claude-plugins-official under Apache-2.0. Non-blocking — the file is written and the warning rides back to the model in the next turn so it can self-correct."
|
|
author: "Anthropic (patterns, Apache-2.0) / NousResearch (Hermes plugin port)"
|
|
hooks:
|
|
- transform_tool_result
|
|
- pre_tool_call
|