architect
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill focuses on generating documentation (SPEC.md and DESIGN.md) and Mermaid diagrams based on user input. It operates entirely within the project's documentation directories and does not utilize network tools or execute system commands.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user ideas and requirements to generate documentation, which represents a potential attack surface for indirect prompt injection.
- Ingestion points: User-provided ideas and feature requests during the hearing phase (Phase 1).
- Boundary markers: The instructions do not specify the use of delimiters or specific markers to isolate untrusted user input within the generated documentation templates.
- Capability inventory: The skill writes files to the
docs/dev/directory but lacks the capability to execute the content it writes or perform network operations. - Sanitization: No input validation or sanitization logic is present for the user-supplied text before it is incorporated into the Markdown files.
Audit Metadata