codependix-navigate

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the codependix CLI to perform dependency analysis and update report artifacts through commands like path and map.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes information from local source files and README documentation which represents a potential attack surface for indirect instructions.
  • Ingestion points: Data is ingested from project README files and command line outputs.
  • Boundary markers: The skill identifies content between <!-- codependix:start --> markers in documentation.
  • Capability inventory: The agent is instructed to execute CLI commands and perform file system writes for graph updates.
  • Sanitization: No explicit sanitization of the ingested graph data or README content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 01:55 PM