explain
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is instructed to read supplied material and repository files to ground its explanations. This creates a surface where malicious instructions embedded in the analyzed code or documentation could attempt to influence the agent's behavior.
- Ingestion points: The skill reads repository files and user-supplied content (SKILL.md: "Read the relevant supplied material or repository files").
- Boundary markers: No specific delimiters or safety instructions are defined to separate user data from instructions.
- Capability inventory: The skill can read files and generate code/visuals.
- Sanitization: No specific sanitization or filtering of external content is mentioned.
- [DYNAMIC_EXECUTION]: The instructions encourage the agent to generate interactive HTML, SVG, and Mermaid diagrams to explain concepts. Generating executable scripts or complex markup for rendering constitutes dynamic code generation, which could be misused if the generated content includes instructions derived from untrusted input.
Audit Metadata