work-with-creators-creator-discovery
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and analyze data from various external platforms, which could contain instructions intended to manipulate the agent.
- Ingestion points: Profile bios, comments, and hashtag pages from TikTok, Instagram, and YouTube, as well as general web search results detailed in steps 1, 2, and 4 of SKILL.md.
- Boundary markers: There are no instructions to wrap external content in delimiters or to ignore potential commands embedded in creator profiles.
- Capability inventory: The skill utilizes browsing and text-reading capabilities to gather information for building and screening creator lists.
- Sanitization: No mechanisms for sanitizing or validating the safety of external text are specified before the information is used to rank and vet finalists.
Audit Metadata