teach-me
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user input and session-specific code to generate "durable artifacts" (learning records, glossaries, and walkthrough documentation). This creates a surface for indirect prompt injection if the source material contains malicious instructions meant to influence the agent's output or documentation style.
- Ingestion points: Processes user explanations and session artifacts as described in
SKILL.mdandwalkthrough-doc.md. - Boundary markers: No specific delimiters or instructions are used to separate untrusted data from the agent's internal logic during the creation of artifacts.
- Capability inventory: The skill possesses file-writing capabilities to save records to the user's environment (e.g., notes vaults or repositories).
- Sanitization: The instructions lack specific validation or sanitization steps for the data being documented.
Audit Metadata