grill-with-docs
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill is designed to analyze codebase documentation and interview the user to refine design plans. While it interacts with project files, it follows standard practices for a development tool and contains no malicious code, unauthorized network calls, or exfiltration patterns.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by design, as it must ingest and process untrusted documentation files from the user's codebase. This is a common characteristic of code-analysis tools. Ingestion points: The skill reads CONTEXT.md, CONTEXT-MAP.md, and Architecture Decision Records (ADRs) from the repository as specified in SKILL.md. Boundary markers: There are no specific boundary markers or instructions to disregard potential malicious directives within the processed files. Capability inventory: The agent is instructed to read files, write to CONTEXT.md and ADR files, and create directories in .aix/ using standard file operations. Sanitization: No explicit sanitization or validation is applied to the content read from the files before processing.
Audit Metadata