dependency-doctor

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • PROMPT_INJECTION (LOW): The skill exhibits an indirect prompt injection surface because its primary function involves processing external, untrusted data from project manifest files and recommending actions based on that data.
  • Ingestion points: Project manifests including package.json, requirements.txt, Cargo.toml, and go.mod (Workflow Step 1).
  • Boundary markers: Absent; no specific delimiters or instructions are provided to the agent to ignore embedded instructions within manifest files.
  • Capability inventory: The skill utilizes standard package manager commands (npm, yarn, pnpm, pip) for installation and updates, which could be leveraged if an injection is successful.
  • Sanitization: Absent; there is no instruction for the agent to sanitize or validate the content of the manifests before processing.
  • COMMAND_EXECUTION (SAFE): Use of package manager commands is appropriate and necessary for the skill's stated purpose of auditing and resolving dependency issues.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:59 PM