codanna-codebase-intelligence

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to ingest and analyze external content from the user's codebase, which could contain instructions designed to manipulate the agent.
  • Ingestion points: Source code and documentation are indexed and read using tools like semantic_search_docs, find_symbol, and search_documents.
  • Boundary markers: The provided instructions do not specify any delimiters or instructions for the agent to ignore potentially malicious content embedded within the indexed code.
  • Capability inventory: The skill provides structural code analysis and relationship tracing through the codanna MCP interface.
  • Sanitization: No sanitization or validation of the retrieved code content is mentioned before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 12:41 PM
Security Audit — agent-trust-hub — codanna-codebase-intelligence