threads-audience-insights
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes untrusted external data from Threads (Meta) posts, bios, and engagement metrics. \n
- Ingestion points: Data enters the context via the
fetch_niche_postsandfetch_profilemethods (SKILL.md). \n - Boundary markers: The instructions do not specify explicit delimiters or instructions to the agent to disregard potential commands within the fetched content. \n
- Capability inventory: The skill uses network operations to read data but lacks write access or command execution capabilities. \n
- Sanitization: There is no evidence of sanitization or filtering of the retrieved social media content before it is processed. \n- [EXTERNAL_DOWNLOADS]: The skill integrates with Apify, a well-known service, to fetch social media data. This interaction is central to the skill's intended purpose of providing data-driven insights.
Audit Metadata