creative-brief
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input from the conversation history to generate a structured project brief.
- Ingestion points: User-provided facts and context are pulled from the conversation history as instructed in the workflow section of
SKILL.md("Read the conversation. Pull every fact already given"). - Boundary markers: The instructions lack specific requirements for using delimiters or boundary markers to segregate user data from the generated brief's structure.
- Capability inventory: The skill is authorized to write the generated markdown content to a local file, specifically
creative-brief.md, as defined in the delivery step ofSKILL.md. - Sanitization: There are no instructions for the agent to sanitize, escape, or filter the content ingested from the conversation before including it in the output file.
Audit Metadata