evidence-artifact-collector

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to run a local generator script, plugins/grc-engineer/scripts/collect-evidence.js, which is consistent with its primary purpose of generating audit artifacts.
  • [DYNAMIC_EXECUTION]: The skill produces Python and Bash scripts dynamically based on user-supplied control IDs or descriptions.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided strings to generate specialized scripts.
  • Ingestion points: User input provided as arguments to the evidence collection script in SKILL.md.
  • Boundary markers: Not explicitly defined in the documentation.
  • Capability inventory: The skill has access to shell and file management tools (Bash, Write, Edit, Read).
  • Sanitization: Standard generation patterns are used; specific sanitization logic resides in the generator script itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 12:27 PM
Security Audit — agent-trust-hub — evidence-artifact-collector