fnl-verification

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional documentation and procedural guidelines for task verification and testing workflows. No malicious patterns or executable code blocks were detected.
  • [DATA_EXPOSURE]: The skill promotes security-positive behavior by instructing the agent to ensure that 'no unrelated edits, secrets, env files' are included in code diffs before accepting work.
  • [COMMAND_EXECUTION]: Contains a benign shell snippet for a directory-based locking mechanism (until mkdir "$LOCK"; do sleep 15; done) intended to prevent overlapping heavy test jobs. This is a standard process synchronization pattern.
  • [EXTERNAL_DOWNLOADS]: Mentions external resources at github.com/mattpocock/skills as a reference for related verification skills, but does not perform any automated downloads or execution from this source.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 03:19 PM