Global Podcast Strategist
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and analyze data from untrusted external sources, which creates a potential surface for indirect prompt injection.
- Ingestion points: The workflow involves mining data from "Apple Podcasts reviews," "listener question pools," and "community hubs" (Discord, Circle, Slack) as described in Phase 2, Phase 4, and the Crisis Management sections.
- Boundary markers: The instructions do not define delimiters or specific "ignore" markers to prevent the agent from executing instructions potentially hidden within listener feedback.
- Capability inventory: The skill is purely documentation-based and does not include scripts or code that perform subprocess calls or network operations directly.
- Sanitization: The skill lacks guidance on sanitizing or validating external content before it is processed by the agent.
Audit Metadata