xrk-http-api
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No evidence of instructions designed to bypass safety guidelines, override system constraints, or extract internal instructions was found. The skill uses natural instructional language to define its role.
- [DATA_EXFILTRATION]: No network operations (e.g., curl, wget, fetch) or sensitive file access patterns were detected. The mention of 'system-level API Key' and 'Bot.checkApiAuthorization' is instructional and refers to the project's internal security conventions rather than a request to extract credentials.
- [EXTERNAL_DOWNLOADS]: The skill does not perform any external package installations or remote script downloads. All referenced documentation and code paths are local to the project (e.g., docs/, src/, core/).
- [COMMAND_EXECUTION]: No shell commands, subprocess spawning, or dynamic code execution patterns were identified in the instructions.
- [SAFE]: The skill appears to be a legitimate development helper for a specific software framework (XRK-AGT), focusing on consistency in API response formatting and module structure.
Audit Metadata