write-spec
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes 'approved grill summaries' or 'user-supplied designs' to generate its output. This creates a surface where malicious instructions embedded in the design document could influence the agent's behavior.
- Ingestion points: The skill explicitly instructs the agent to use 'approved grill summary or user-supplied design' as the source for the specification (SKILL.md, Workflow step 1).
- Boundary markers: The instructions lack explicit boundary markers or warnings to the agent to disregard any instructions found within the design source material.
- Capability inventory: The skill is intended to write documentation to the file system, typically under the
docs/creed/specs/directory. - Sanitization: There is no mention of sanitizing or validating the input data before it is interpolated into the final document structure.
Audit Metadata