npm-publishing

Pass

Audited by Gen Agent Trust Hub on Oct 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing external repository data while possessing sensitive capabilities.
  • Ingestion points: The skill reads local project files using cat package.json and ls -la, and fetches external registry data via npm view and npm access.
  • Boundary markers: There are no explicit instructions or delimiters provided to help the agent distinguish between the content of repository files and its own system instructions.
  • Capability inventory: The skill uses the run_command tool, providing the agent with shell access, and performs sensitive operations like npm publish and npm trust which utilize user credentials or OIDC tokens.
  • Sanitization: The skill lacks logic to sanitize or validate the values retrieved from package.json (such as scripts or version strings) before they are used in command construction or decision-making.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 19, 2026, 06:24 PM