afk-static-review

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes output from external linting and typechecking tools, which creates a surface where instructions embedded in code comments or tool errors could potentially influence the agent's behavior during the review process.
  • Ingestion points: scripts/changed-files.sh (which reads git status and diffs) and the output from the repository's lint and typecheck commands as specified in SKILL.md.
  • Boundary markers: Absent. The instructions do not specify delimiters or constraints to isolate the external tool output from the agent's primary instructions.
  • Capability inventory: The skill executes a provided shell script (scripts/changed-files.sh) and instructions prompt the agent to run arbitrary linting/typechecking commands found within the user's repository.
  • Sanitization: Absent. There is no evidence of filtering or validation of the text returned by the external tools before it is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 01:32 AM
Security Audit — agent-trust-hub — afk-static-review