architecture-documenter
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest, analyze, and summarize potentially untrusted technical descriptions, system architecture details, or source code provided by users.
- Ingestion points: The skill processes system architecture details, component descriptions, and technical decision context provided during user interaction to generate documentation and ADRs.
- Boundary markers: The instructions do not define explicit delimiters or instructions for the AI to ignore instructions potentially embedded within the architectural data it analyzes.
- Capability inventory: The skill is primarily focused on text and diagram generation and does not request access to high-risk tools such as network operations or shell execution in its instructions or metadata.
- Sanitization: There are no specific instructions to sanitize or validate the content of the technical data provided for documentation generation.
Audit Metadata