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
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:30 AM
Security Audit — agent-trust-hub — codebase-summarizer