technical-design
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external inputs such as product scope and existing codebase content to generate technical specifications.
- Ingestion points: Instructions in SKILL.md direct the agent to consume 'approved product scope, applicable approved design direction, existing code and stack'.
- Boundary markers: The instructions lack explicit boundary markers or delimiters to separate untrusted external data from agent instructions.
- Capability inventory: The skill instructs the agent to perform file writing operations to create or update 'docs/tech-spec.md'.
- Sanitization: There are no provided instructions for sanitizing, escaping, or validating the input data before it is incorporated into the technical documentation.
Audit Metadata