grill-with-docs
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns were detected. The skill's behavior is consistent with its description, focusing on domain modeling and local documentation management.
- [DATA_EXPOSURE]: The skill reads project documentation and source code to verify domain logic. This file access is limited to the project directory for legitimate analysis and does not target sensitive system files or credentials.
- [COMMAND_EXECUTION]: The skill does not perform any shell command execution or system-level modifications.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local files (codebase and documentation), which is an inherent surface for indirect prompt injection. However, given the skill's specific purpose and lack of high-risk capabilities like network access or arbitrary code execution, this represents a negligible risk.
Audit Metadata