pp-reno-goat

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

• Third-party content exposure detected (low risk: 0.10). The skill’s required runtime workflow ingests only user-supplied CLI arguments/URLs/queries to fetch upstream product/search/delivery data (e.g., product, compare, product-search, find-similar, source-probe), which can include attacker-authored free text but requires the workflow to actively select/fetch specific items based on those inputs rather than consuming an always-on outsider text feed.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill includes install commands that fetch and execute remote code (npx @mvanhorn/printing-press-library and go install github.com/mvanhorn/printing-press-library/.../reno-goat-pp-cli@latest and .../reno-goat-pp-mcp@latest), which are required setup steps that would run external code at runtime.