setup-api-key
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user input intended to be an API key and uses it to perform network requests and file system writes, creating a surface for potential indirect prompt injection attacks.
- Ingestion points: The user-supplied message following Step 1, which the agent is instructed to treat as an API key.
- Boundary markers: The instructions do not define specific delimiters or "ignore embedded instruction" warnings for the user-provided data.
- Capability inventory: The skill performs network GET requests to api.elevenlabs.io and writes data to the local .env file.
- Sanitization: The skill performs a validation check by calling the ElevenLabs API, but it does not specify sanitization or filtering to prevent the agent from interpreting malicious instructions if they are included in the user's response.
Audit Metadata