dependency-doctor

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project manifest files to generate audit reports, which is a standard surface for indirect prompt injection findings.
  • Ingestion points: Manifest files like package.json, requirements.txt, Cargo.toml, and go.mod specified in the Core Workflow.
  • Boundary markers: None identified in the instructions for delimiting or ignoring instructions within manifest files.
  • Capability inventory: The skill suggests execution of various package manager commands (npm, yarn, pnpm, pip) that could be manipulated via malicious package names or version strings.
  • Sanitization: No explicit instructions for sanitizing or escaping package metadata before processing are provided.
  • [COMMAND_EXECUTION]: The skill provides templates and instructions for the agent to identify and recommend shell commands for auditing, updating, and deduplicating dependencies across multiple package management ecosystems.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:30 AM
Security Audit — agent-trust-hub — dependency-doctor