teach-me
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill is composed of natural language instructions focused on instructional design, including the use of mastery checklists and verification of knowledge through interactive questioning.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external and potentially untrusted artifacts (e.g., Pull Requests, code diffs, and ADRs) to explain them to the user.
- Ingestion points: Processes external documentation and code artifacts referenced by the user (SKILL.md).
- Boundary markers: The instructions do not define explicit delimiters or warnings to ignore instructions embedded within the analyzed artifacts.
- Capability inventory: The skill relies on communication tools like
AskUserQuestion. It does not possess capabilities for file writing, network exfiltration, or shell command execution. - Sanitization: No specific sanitization or filtering logic is defined for the analyzed content; the agent relies on its inherent safety guardrails.
Audit Metadata