regex-builder
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates an indirect prompt injection surface by instructing the agent to ingest untrusted user data to generate complex regex patterns and code snippets.
- Ingestion points: The workflow in
SKILL.md(Phase 1) explicitly collects positive and negative examples from the user and context to drive pattern generation. - Boundary markers: The instructions do not define boundary markers or 'ignore' directives to prevent the agent from obeying instructions that might be embedded within the provided string examples.
- Capability inventory: The skill generates functional Python and JavaScript code templates (
SKILL.md) and regex patterns based on the untrusted examples. - Sanitization: The skill lacks mechanisms for sanitizing or validating user-provided examples before they are interpolated into the pattern inference and code generation process.
Audit Metadata