samuel-video-coach

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information regarding video topics and experiments (documented in SKILL.md, Section 6). While this creates an attack surface, the risk is minimized by explicit instructions to mark unverified facts as 'to-be-confirmed', a lack of high-privilege tools, and the inclusion of privacy protection guidelines in references/beginner-coach-mode.md. This ingestion is limited to text generation for planning purposes.\n- [EXTERNAL_DOWNLOADS]: The scripts/validate_storyboard.py script references the jsonschema library. This is a well-known standard package from a trusted public registry (PyPI) and is used for its intended purpose of validating generated JSON data against the provided schema.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 12:59 AM
Security Audit — agent-trust-hub — samuel-video-coach