pp-medium-reader

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

• Third-party content exposure detected (medium risk: 0.30). The skill uses the medium-reader-pp-cli HTTP client to read Medium content from user-supplied selectors like feed <@user|publication|tag>, read <url|id>, and search <query>, so outsider-authored free text from Medium pages/RSS/Search results can be ingested at runtime when the user/agent chooses those inputs.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's required installation steps run go install against GitHub module paths (github.com/mvanhorn/printing-press-library/library/media-and-entertainment/medium-reader/cmd/medium-reader-pp-cli@latest and github.com/mvanhorn/printing-press-library/library/media-and-entertainment/medium-reader/cmd/medium-reader-pp-mcp@latest), which fetches remote code and compiles/executes it as a required dependency.