pp-tenderned

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

• Third-party content exposure detected (high risk: 0.90). The skill invokes the tenderned-pp-cli to fetch and ingest content from the public TenderNed platform (see SKILL.md commands like notices list, docs get/docs download, and docs grep), so the agent will read arbitrary public notices and attached PDFs/Word docs that could contain untrusted instructions and materially influence subsequent actions (including webhook delivery).

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's prerequisite instructs running "npx -y @mvanhorn/printing-press install tenderned --cli-only", which fetches and executes remote code from the npm registry (e.g. https://registry.npmjs.org/@mvanhorn/printing-press) and is required for the CLI to function, so it can execute remote code at runtime.