codebase-summarizer
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository files it is instructed to analyze.\n
- Ingestion points: Recursive analysis of the folder tree and file organization (SKILL.md, Core Workflow).\n
- Boundary markers: The skill does not provide specific instructions to the agent to use delimiters or to ignore embedded commands within the scanned codebase.\n
- Capability inventory: The skill performs file system reads and documentation generation; it does not request high-risk tools like network access or arbitrary code execution in its frontmatter.\n
- Sanitization: There are no instructions for sanitizing, escaping, or filtering content from the codebase before it is incorporated into the architecture summary.
Audit Metadata