architect-generate-agent
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill documents a legitimate workflow for creating agents on the ElevenLabs platform using its official REST API.\n- [DATA_EXPOSURE]: It references the official vendor domain (api.elevenlabs.io) and correctly suggests using an environment variable placeholder ($API_KEY) for authentication, following security best practices for credential management.\n- [INDIRECT_PROMPT_INJECTION]: The skill involves generating agent system prompts based on user descriptions. The recommended process includes a synthesis and confirmation step (Step 2) to ensure the user's intent is accurately reflected and to provide an opportunity for manual review of the proposed prompt content.
Audit Metadata