dependency-auditor

Warn

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill documentation in SKILL.md and README.md specifies the execution of Python scripts such as dep_scanner.py and license_checker.py. These scripts are not part of the provided file set, presenting a risk of executing unverified code.
  • [EXTERNAL_DOWNLOADS]: The skill claims to integrate with external/proprietary vulnerability feeds and databases, which may involve network operations to fetch data from untrusted or unverified remote sources.
  • [PROMPT_INJECTION]: The skill analyzes untrusted external data from project manifests, creating an indirect prompt injection vulnerability. 1. Ingestion points: Project files like package.json, requirements.txt, and others listed in SKILL.md. 2. Boundary markers: None identified; the agent is not instructed to treat manifest content as data only. 3. Capability inventory: Script execution and file system access. 4. Sanitization: No content validation or escaping of parsed data is described.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 5, 2026, 08:07 PM
Security Audit — agent-trust-hub — dependency-auditor