skill-provenance

Pass

Audited by Gen Agent Trust Hub on Jul 4, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines a workflow for executing a local script fdk/tools/skill-provenance.py using the Python interpreter. This is the intended functionality for auditing skill sources and verifying file integrity.
  • [PROMPT_INJECTION]: The skill's instructions document an interface where skill names and repository URLs are provided as arguments to shell commands. While this presents an interpolation surface (indirect prompt injection), it is a standard pattern for the skill's primary purpose of security auditing.
  • Ingestion points: Skill names and source URL parameters within SKILL.md instructions.
  • Boundary markers: None present in the command examples.
  • Capability inventory: Execution of the local skill-provenance.py script via python3 subprocesses.
  • Sanitization: Not explicitly detailed in the instructional markdown.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 4, 2026, 06:03 AM
Security Audit — agent-trust-hub — skill-provenance