cy-create-techspec
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from project files and user interactions to generate technical specifications and decision records, which creates a potential surface for indirect prompt injection.
- Ingestion points: Reads
_prd.mdand_techspec.mdfiles from the.compozy/tasks/<name>/directory; processes interactive user responses to technical clarification questions. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external file content as untrusted or to ignore potential embedded instructions.
- Capability inventory: The skill performs file system read and write operations within the project directory (creating ADRs and TechSpecs) and invokes tools to explore the codebase architecture.
- Sanitization: No explicit sanitization or validation of the PRD content or user responses is performed before interpolation into the design documents.
Audit Metadata