list-npm-package-content

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • Command Execution: The skill script executes shell commands to build and package the project.
  • Evidence: scripts/list-package-files.sh calls pnpm build and pnpm pack. These commands execute scripts and logic defined in the local project's configuration to generate the distribution artifact, which is a standard procedure for package verification.
  • Indirect Prompt Injection Surface: The skill processes and displays filenames found within the package.
  • Ingestion points: File names are read from the tarball output of tar -tzf in scripts/list-package-files.sh and presented to the agent.
  • Boundary markers: The output is provided as raw text without specific delimiters or instructions to the agent to treat the content as untrusted data.
  • Capability inventory: The skill performs local file system operations including building, packing, and deleting temporary tarball files.
  • Sanitization: The script lists raw filenames without sanitization, which is the intended behavior for debugging package contents.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 01:43 AM