explaining-code
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for the agent on how to explain code to a user. It does not include any scripts, command execution, or external dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data (source code), which presents a potential surface for indirect prompt injection. However, the skill lacks any dangerous capabilities (such as file writing or network access) that could be exploited through this vector.
- Ingestion points: The skill processes code snippets provided by the user or found in the codebase.
- Boundary markers: None present.
- Capability inventory: None. The skill only generates text-based explanations and ASCII diagrams.
- Sanitization: None present.
Audit Metadata