context-layer-health-check

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from git logs and wiki files to identify health issues, creating an attack surface where embedded instructions could influence agent behavior.
  • Ingestion points: The agent reads 'git log --merges' to find 'wiki-miss:' lines and reviews wiki pages for contradictory claims or stale priorities.
  • Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' warnings to isolate the processed data from the agent's task context.
  • Capability inventory: The agent has the authority to modify wiki files ('Fix what evidence supports') and execute the 'scripts/lint' utility.
  • Sanitization: Absent. The skill performs semantic reviews and applies changes based on external findings without explicit sanitization or validation of the input data.
  • [COMMAND_EXECUTION]: The skill relies on the execution of local system commands and repository-specific scripts.
  • Evidence: The agent is instructed to run 'git log --merges', 'scripts/lint', and 'scripts/lint --report'.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 07:58 AM
Security Audit — agent-trust-hub — context-layer-health-check