content-strategy
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface.
- Ingestion points: Untrusted data enters the agent context through keyword exports, sales transcripts, survey responses, and forum/competitor research via web search in SKILL.md.
- Boundary markers: No delimiters or 'ignore' warnings are provided for these data sources.
- Capability inventory: The skill instructs the agent to process data into tables and summaries; the agent likely possesses file-writing and web-navigation tools.
- Sanitization: There is no instruction for escaping or validating external content before processing.
Audit Metadata