regex-builder
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided positive and negative examples to generate patterns. This represents a data ingestion surface.
- Ingestion points: Example collection phase described in
SKILL.md. - Boundary markers: No specific delimiters or safety instructions are defined for processing user examples.
- Capability inventory: The skill lacks tool invocations, network access, or file-writing capabilities; it is limited to text generation.
- Sanitization: No explicit sanitization of input examples is performed, though the output is restricted to regex patterns and documentation.
Audit Metadata