pp-pypi

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The skill reads PyPI package metadata and RSS feeds via CLI, which ingest package names and descriptions created by third-party PyPI authors.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to install an external CLI and MCP server via npm and Go from GitHub (github.com/mvanhorn/printing-press-library), which represents an unverified runtime external dependency from a personal/unofficial repository.