test
Pass
Audited by Gen Agent Trust Hub on Nov 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill takes an external parameter [PluginName] which is used in file paths and status updates.
- Ingestion points: PluginName parameter via /test trigger.
- Boundary markers: None present in the SKILL.md definition.
- Capability inventory: Local file writing (status.json) and execution of internal testing workflows (build validation, DAW compatibility).
- Sanitization: No input validation or escaping is defined in this file.
- [SAFE]: No malicious patterns or security risks were identified. The skill is purely orchestrational, referencing trusted internal paths for plugin development tasks.
Audit Metadata