Raeli Savitt 95b6bd5df6 Harden agent attack surface: scan writes to memory, skills, cron, and context files ... The security scanner (skills_guard.py) was only wired into the hub install path. All other write paths to persistent state — skills created by the agent, memory entries, cron prompts, and context files — bypassed it entirely. This closes those gaps: - file_operations: deny-list blocks writes to ~/.ssh, ~/.aws, ~/.hermes/.env, etc. - code_execution_tool: filter secret env vars from sandbox child process - skill_manager_tool: wire scan_skill() into create/edit/patch/write_file with rollback - skills_guard: add "agent-created" trust level (same policy as community) - memory_tool: scan content for injection/exfil before system prompt injection - prompt_builder: scan AGENTS.md, .cursorrules, SOUL.md for prompt injection - cronjob_tools: scan cron prompts for critical threats before scheduling Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>		2026-02-25 23:43:15 -05:00
..
__init__.py	Refactor Terminal and AIAgent cleanup	2026-02-21 22:31:43 -08:00
auxiliary_client.py	refactor: integrate Nous Portal support in auxiliary client	2026-02-25 18:39:36 -08:00
context_compressor.py	Hermes Agent UX Improvements	2026-02-22 02:16:11 -08:00
display.py	refactor: update failure message handling in display module and add debug logging in code execution tool	2026-02-24 14:25:53 -08:00
model_metadata.py	Refactor Terminal and AIAgent cleanup	2026-02-21 22:31:43 -08:00
prompt_builder.py	Harden agent attack surface: scan writes to memory, skills, cron, and context files	2026-02-25 23:43:15 -05:00
prompt_caching.py	Refactor Terminal and AIAgent cleanup	2026-02-21 22:31:43 -08:00
trajectory.py	Refactor Terminal and AIAgent cleanup	2026-02-21 22:31:43 -08:00