product-appeal-analyzer

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to "WebFetch the target URL to analyze live content" in SKILL.md and supports running scripts like python scripts/appeal_scorer.py <url>, which requires fetching and reading arbitrary public landing pages (untrusted third‑party content) as part of its analysis.