amazon-listing-optimization

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and parses public Amazon product pages (via scripts/fetch-listing.sh which curl's https://{domain}/dp/{ASIN}) and uses web_search/site:amazon.com to ingest competitor listing content, then extracts keywords and uses those extracted, untrusted, user-generated page contents to drive keyword selection and rewrite listings—so third-party pages can materially influence the agent's actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The scripts/fetch-listing.sh script performs runtime curl fetches of Amazon product pages (e.g., https://www.amazon.com/dp/{ASIN} and other marketplace domains) and the retrieved HTML is parsed to extract competitor keywords that are injected into the skill's prompt/keyword inputs, so this external content directly controls the agent's prompts at runtime.