ad-library-teardown
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes the
WebFetchtool to retrieve ad data from various vendor-provided endpoints (e.g.,/v1/facebook/adLibrary/search/ads). These operations are consistent with the skill's stated purpose of social media research. - [PROMPT_INJECTION]: As the skill processes external, untrusted content such as ad copy and video transcripts, there is an inherent surface for indirect prompt injection. This is a common characteristic of web-scraping tools and is mitigated by the skill's analytical focus.
- [CREDENTIALS_UNSAFE]: The skill requires a
SCRAPECREATORS_API_KEYto function. This environment variable is used for authenticating with the developer's own API services, which is a standard and acceptable practice for service-integrated skills.
Audit Metadata