content-idea-generator
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted user data to guide its reasoning and search parameters without explicit boundary markers. Ingestion points: Positioning statements, ICP frustrations, and proof points within context loading gates in SKILL.md. Boundary markers: None present to isolate user inputs from instructions. Capability inventory: The agent can perform tool calls via web_search() in SKILL.md. Sanitization: No escaping or validation is performed on the ingested data before it is processed by the model or used in search queries.
Audit Metadata