architect-create-llm-test
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill interacts exclusively with official ElevenLabs infrastructure at api.elevenlabs.io, representing standard vendor functionality.
- [SAFE]: Secret management is handled correctly by using the $API_KEY placeholder for authentication headers rather than hardcoding credentials.
- [SAFE]: The skill includes explicit security and privacy warnings regarding the handling of Personally Identifiable Information (PII) when reading conversation transcripts from the API.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources (conversation history) which could contain instructions.
- Ingestion points: GET requests to conversation endpoints in SKILL.md.
- Boundary markers: None present.
- Capability inventory: curl POST commands to the testing API in SKILL.md.
- Sanitization: None defined.
Audit Metadata