architecture-md
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and interpret arbitrary files from a codebase (e.g., README, package manifests, and source code) to generate a document. This creates a surface for indirect prompt injection if those files contain instructions designed to override agent behavior.\n
- Ingestion points: Files are read in Step 1 of the SKILL.md workflow ('Explore the Codebase').\n
- Boundary markers: The instructions lack explicit delimiters or guidance for the agent to treat file content strictly as data rather than instructions.\n
- Capability inventory: The workflow utilizes file discovery (tree, glob) and reading tools to explore the codebase.\n
- Sanitization: There are no sanitization steps defined for the content extracted from the files before processing.
Audit Metadata