cy-idea-factory
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection through its ingestion of external data.
- Ingestion points: Untrusted data enters the agent context through web search results during the research phase (Step 3) and codebase exploration.
- Boundary markers: There are no instructions to use delimiters or ignore embedded instructions when processing the results from web tools or codebase reads.
- Capability inventory: The agent has the ability to create directories and write files (.compozy/tasks//_idea.md, .compozy/tasks//adrs/) based on the processed content.
- Sanitization: The skill lacks explicit sanitization or validation steps for the content retrieved from external sources before it is drafted into the final specification.
Audit Metadata