amazon-listing-optimization

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and scrapes public Amazon product pages (see scripts/fetch-listing.sh) and uses web_search/competitor ASINs described in SKILL.md to extract titles, bullets, and reviews that the agent ingests and uses to prioritize keywords and generate/modify listing copy, which creates a clear vector for indirect prompt injection from untrusted third‑party content.

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

• Potentially malicious external URL detected (high risk: 0.80). The bundled script fetches competitor product pages at runtime (e.g., https://www.amazon.com/dp/ and equivalent marketplace domains) via curl and the extracted HTML is parsed and injected as listing/keyword input that directly controls the agent's prompt/outputs, so this is a runtime external dependency that influences model behavior.