content-strategy
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process external data such as keyword exports, sales call transcripts, survey responses, and forum content. This ingestion of untrusted data represents a potential attack surface for indirect prompt injection if the content contains instructions designed to manipulate the agent.
- Ingestion points: SKILL.md (Content Ideation Sources section).
- Boundary markers: None present to delimit external data from instructions.
- Capability inventory: The skill focuses on analysis and planning and does not possess high-risk capabilities like arbitrary command execution, file system writes, or direct network operations (beyond standard web search).
- Sanitization: No explicit sanitization or filtering of external input is mentioned.
Audit Metadata