explain-code
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides formatting and pedagogical guidelines for explaining code. It does not include any executable code, network operations, or sensitive data access.
- [SAFE]: The metadata and instructions are consistent with the stated purpose of code explanation and teaching.
- [SAFE]: The skill includes safety-conscious instructions, explicitly advising against using the skill for modifying code, fixing bugs, or generating new implementations.
- [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for indirect prompt injection because it instructs the agent to read external files and modules referenced in code. However, the risk is minimal given the skill's restricted scope to explanation only.
- Ingestion points: The agent is instructed to read external files/modules referenced in the code being explained.
- Boundary markers: None provided.
- Capability inventory: Relies on the agent's file-reading capabilities.
- Sanitization: None provided.
Audit Metadata