find-twitter-influencers
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface.
- Ingestion points: Untrusted content is fetched from external APIs, specifically search listicles via Exa and user profiles via Twitter (manifest.json steps 3, 4, 5, and 6).
- Boundary markers: The instructions do not define delimiters or provide guidance to the agent to disregard instructions potentially hidden in the external data.
- Capability inventory: The skill's functionality is limited to data analysis and rendering a markdown table, with no access to dangerous system calls, shell execution, or sensitive file system operations.
- Sanitization: No validation or sanitization steps are performed on the data retrieved from external sources prior to processing by the agent.
Audit Metadata