legal-pages
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional text defining a methodology for generating legal documentation from code analysis. It does not execute commands, download external resources, or handle sensitive credentials.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for the agent to analyze potentially untrusted data from the codebase to generate text. This represents a standard auditing surface inherent to the skill's purpose. 1. Ingestion points: Source code, database schema, environment configuration, and browser storage state (SKILL.md). 2. Boundary markers: Absent; instructions do not specify delimiters for analyzed content. 3. Capability inventory: File system access for code review and inspection of application state. 4. Sanitization: The workflow requires final human approval ('What the owner does by hand') before any generated text is published.
Audit Metadata