course-review
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill naturally incorporates an indirect prompt injection surface because its primary function is to analyze external, potentially untrusted, course content.
- Ingestion points: SKILL.md requests full course text, slides, and CTAs in Step 1.
- Boundary markers: No delimiters or 'ignore embedded instructions' warnings are used in the prompt logic to isolate external data.
- Capability inventory: No high-risk capabilities such as network exfiltration, file system manipulation, or arbitrary code execution were detected.
- Sanitization: The skill does not perform validation or sanitization on the ingested course material.
Audit Metadata