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