curate
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill is designed for documentation and only interacts with the local filesystem in a non-sensitive project directory.
- [DATA_EXFILTRATION]: The skill performs local file writes to
.gauntlet/annotations/but contains no network capabilities, remote connections, or instructions to transmit data externally. - [PROMPT_INJECTION]: The instructions are strictly task-oriented and do not attempt to override agent constraints, bypass safety filters, or disclose system prompts.
Audit Metadata