task-routing

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified. The skill is a legitimate routing and reference tool.
  • [COMMAND_EXECUTION]: The skill documents various playdrop CLI command families, which are standard vendor tools for the Playdrop platform.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. Ingestion points: playdrop documentation browse/read (SKILL.md). Boundary markers: Absent. Capability inventory: playdrop project create/publish (references/cli-map.md). Sanitization: Absent. This is considered safe as it involves reading official platform documentation for routing purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 06:39 PM