dev-dependency-management

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill includes a Python script, scripts/dep_auditor.py, and instructions for the agent to perform dependency audits by processing manifest files. This creates a surface for indirect prompt injection if an attacker-controlled manifest file contains malicious strings designed to influence the agent when it reads the audit results.
  • Ingestion points: scripts/dep_auditor.py ingests JSON manifest data from a file path provided via the --input command-line argument.
  • Boundary markers: The script generates Markdown reports but does not implement delimiters or safety instructions to prevent the agent from interpreting manifest-derived content as instructions.
  • Capability inventory: The skill allows for reading manifest files and writing report files. The agent's subsequent processing of these reports presents the primary risk vector.
  • Sanitization: Manifest data (such as package names or descriptions) is included in the output report without escaping or sanitization.
  • [EXTERNAL_DOWNLOADS]: The skill references numerous external resources, including official documentation, security alerts, and standards from reputable organizations such as CISA, NIST, the European Commission, and various official package manager projects. These references are used for informational purposes and to verify security behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 02:03 PM