tools-registry-context
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local scripts (drift.sh, build-map.py) and standard git commands (git log, git status) to perform its primary function of documentation synchronization and context loading. The scripts are bundled with the skill and do not perform network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests untrusted data from the docs/context/ directory. 1. Ingestion points: Documentation fragments in docs/context/, git logs, and repository status. 2. Boundary markers: None explicitly defined to separate data from instructions. 3. Capability inventory: Local script execution via bash/python3 and file system writes to update mappings. 4. Sanitization: No formal sanitization or filtering of ingested documentation content is performed before processing or display.
Audit Metadata