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.shand the textual output (stdout/stderr) from linting and type-checking tools inSKILL.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.shscript correctly implements security best practices for handling file paths by using null-terminated strings (-z) andIFS= read -r -d ''to prevent word-splitting or injection via malicious filenames.
Audit Metadata