meta-ads-analyser

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

• Third-party content exposure detected (high risk: 0.70). The skill's required workflow explicitly reads and analyzes ad creatives and landing-page screenshots extracted from the public Meta Ad Library (via /meta_ads_extractor and the assets folder ~/clawd/output/meta-ads/...), so untrusted third-party content is ingested and used to drive analysis and reporting which could be influenced by embedded instructions or content.