pp-npm

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the npm-pp-cli tool, which is fetched from the vendor's resources using npx from @mvanhorn/printing-press-library or go install from github.com/mvanhorn/printing-press-library.
  • [REMOTE_CODE_EXECUTION]: The setup process executes code downloaded from external sources through npx and the Go toolchain to install the required CLI binary.
  • [DATA_EXFILTRATION]: The CLI tool includes a built-in --deliver webhook:<url> flag, enabling the agent to transmit command results directly to any user-specified external URL.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute the npm-pp-cli binary with arguments and subcommands derived from user queries.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from the public npm registry, which serves as an untrusted ingestion point for potentially malicious instructions embedded in package metadata.
  • Ingestion points: Fetches package descriptions, maintainer info, and dependency data from the npm registry via npm-pp-cli (SKILL.md).
  • Boundary markers: Absent; the skill does not specify delimiters or instructions to ignore embedded directives in the registry data.
  • Capability inventory: Uses the Bash tool for command execution and supports writing to files or webhooks.
  • Sanitization: None described for the external content processed by the tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 10:55 AM
Security Audit — agent-trust-hub — pp-npm