use-design-check
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security concerns identified. The skill defines a procedural check for the agent to follow using logic-based evaluation criteria to determine whether to run a design command.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to inspect local project files using tools like 'Read', 'Grep', and 'Glob'. While these files are technically untrusted external data, the skill does not include any capabilities (such as network access, file writing, or command execution) that would make this ingestion surface exploitable.
- Ingestion points: The skill body instructs the agent to read sibling or source files to evaluate criteria.
- Boundary markers: None present.
- Capability inventory: Limited to read-only tools ('Read', 'Grep', 'Glob') specified in the YAML frontmatter.
- Sanitization: Not applicable as the skill only generates a decision string ('RUN /design' or 'SKIP /design').
Audit Metadata