regex-builder
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Command Execution (SAFE): The skill uses ripgrep and Python locally to validate regular expressions against user-specified files. This behavior is consistent with its stated purpose and does not involve unauthorized access or privilege escalation.
- Dynamic Execution (LOW): The skill generates one-liner Python scripts ('python -c') to inspect regex match groups. This is a low-risk use of dynamic execution as it follows a simple, known template for local debugging.
- Indirect Prompt Injection (LOW): The skill has an attack surface for indirect prompt injection because it reads content from local files. Evidence Chain: 1. Ingestion points: File content read via 'rg' and 'python' in SKILL.md workflow. 2. Boundary markers: Absent; there are no instructions to the agent to disregard instructions found within the data files. 3. Capability inventory: Local command execution (rg, python). 4. Sanitization: Absent; the skill does not suggest sanitizing or escaping the content of the files before processing.
Audit Metadata