docs-with-mermaid
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, such as source code or project topics, to generate architectural diagrams and documentation.
- Ingestion points: The skill accepts a 'topic or file to document' as an argument, which is then processed by the agent to create content.
- Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore or isolate potentially malicious instructions embedded in the user-provided data.
- Capability inventory: While the skill body focuses on documentation, it provides detailed structural templates that could be used to facilitate multi-step chains or downstream tool manipulation if the agent environment includes more powerful capabilities.
- Sanitization: No explicit sanitization, escaping, or validation steps are provided for handling the external content before it is interpolated into the generated documentation.
Audit Metadata