afk-static-check

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to run the repository's existing lint and typecheck commands. This involves executing scripts or binaries defined within the project being analyzed (e.g., in a package.json or Makefile), which is expected behavior for a development tool.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes untrusted data from the repository.
  • Ingestion points: File paths generated by scripts/changed-files.sh and the textual output (stdout/stderr) from linting and type-checking tools in SKILL.md.
  • Boundary markers: Absent. The instructions do not explicitly tell the agent to disregard instructions embedded in the linter findings.
  • Capability inventory: Execution of shell commands to run static analysis tools.
  • Sanitization: The scripts/changed-files.sh script correctly implements security best practices for handling file paths by using null-terminated strings (-z) and IFS= read -r -d '' to prevent word-splitting or injection via malicious filenames.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 01:37 PM
Security Audit — agent-trust-hub — afk-static-check