yaml-master
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, data exfiltration, or obfuscation were detected. The skill's architecture and permissions are aligned with its purpose of managing local YAML configurations.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes external YAML files (ingestion points: .yaml and .yml files read via SKILL.md). It has the capability to modify files and execute system commands (capability inventory: Write, Edit, and Bash tools). While it includes logic to identify risky patterns (sanitization: SKILL.md), it does not explicitly define boundary markers to separate data from instructions during processing.
- [COMMAND_EXECUTION]: The skill requests broad permissions for Bash utility tools (general and util). This capability is used to support validation tasks and the execution of standard linting utilities, which is appropriate for a configuration management skill.
Audit Metadata