lawyerscrib
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates within its intended scope of text processing and linguistic humanization. All analyzed files focus on stylistic improvements for French legal documents without engaging in risky behaviors.
- [PROMPT_INJECTION]: No direct prompt injection or instructions to bypass safety guidelines were detected. The instructions are focused exclusively on professional legal writing standards and linguistic refinement.
- [PROMPT_INJECTION]: The skill processes external text provided by users (legal documents), which represents a surface for indirect prompt injection. However, the risk is mitigated as the skill's primary function is text transformation with manual review steps, and it does not contain instructions to execute arbitrary code derived from the input. Capability inventory: Read, Write, Edit, Grep, Glob (SKILL.md). Ingestion point: User-provided legal text. Sanitization: None explicitly defined. Boundary markers: None explicitly defined.
Audit Metadata