cross-platform-repurposing
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided content (e.g., blog posts, video transcripts) to extract insights, which creates an attack surface for instructions hidden within that content to influence the agent.
- Ingestion points: Content is ingested in the 'Atomize' step (Step 1) to identify core ideas for social media posts.
- Boundary markers: There are no explicit instructions to use delimiters or to disregard instructions found within the source material.
- Capability inventory: The skill coordinates content generation through other tools and facilitates automated scheduling for social platforms.
- Sanitization: No validation or filtering mechanisms are described for the input content.
Audit Metadata