Skills
Navigate
skills/jimmypaolini/codebase/codependix-navigate/Gen Agent Trust Hub

codependix-navigate

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read dependency data from repository files like READMEs or JSON exports. This data ingestion could be leveraged for indirect prompt injection if the source files contain malicious instructions meant to influence the agent.
  • Ingestion points: README sections identified by ## 🕸️ Codependix or <!-- codependix:start --> and their corresponding JSON files.
  • Boundary markers: The skill does not define specific boundary markers or instructions for the agent to ignore potential commands within the ingested graph data.
  • Capability inventory: The agent is instructed to use the codependix CLI tool for graph verification and export.
  • Sanitization: There is no mention of sanitizing or validating the contents of the dependency graphs before processing.
  • [COMMAND_EXECUTION]: The instructions direct the agent to execute shell commands using the codependix CLI, specifically codependix --check and codependix --write, to maintain graph accuracy.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 02:22 AM
Security Audit — agent-trust-hub — codependix-navigate