skill-orchestrator
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The skill primarily serves as a logical router for business workflows.
- [SAFE]: All external references, such as ElevenLabs or Qwen3-TTS for voice design, are used in a legitimate context for productivity and do not involve suspicious downloads or remote code execution.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill does not attempt to access sensitive environment variables, credentials, or system files. It focuses on user-provided business context.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user input to define project goals. It uses structured templates and progress trackers which provide clear boundaries for external data, minimizing the risk of instruction overriding. Ingestion points: user challenge/context input in SKILL.md; Boundary markers: structured Markdown templates and progress tables; Capability inventory: no shell execution, file-write, or network capabilities identified in the skill content; Sanitization: not explicitly implemented.
Audit Metadata