teach
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided information to generate explanations, creating a potential surface for indirect prompt injection.\n
- Ingestion points: User conversation context and specific queries (SKILL.md).\n
- Boundary markers: No specific delimiters or instructions to ignore embedded commands were identified.\n
- Capability inventory: The skill instructions mention running the
how,why, andshow-meskills, and utilizing code, diffs, and debuggers (SKILL.md).\n - Sanitization: No sanitization or validation of the ingested user content is specified.\n- [SAFE]: The skill is primarily instructional and does not contain malicious code, remote script execution, obfuscation, or persistence mechanisms.
Audit Metadata