rightcode-grill-with-docs
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's functionality is limited to documentation management, specifically updating CONTEXT.md and ADR files. It does not exhibit patterns of data exfiltration, network access, or unauthorized command execution.\n- [SAFE]: No obfuscated content, hardcoded credentials, or remote code execution patterns were found. All instructions and templates (ADR-FORMAT.md, CONTEXT-FORMAT.md) are transparent and follow standard development practices.\n- [SAFE]: While the skill exhibits an indirect prompt injection surface by reading codebase content to inform documentation updates, this is essential for its primary purpose. 1. Ingestion: The skill reads local project code and documentation files. 2. Boundary markers: No explicit delimiters for untrusted code content are defined. 3. Capability: The agent has the authority to write and update markdown files. 4. Sanitization: No specific sanitization or validation of the ingested code is described. This surface is considered safe given the intended use-case of a documentation assistant.
Audit Metadata