architect-branches-versions-merge
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill interacts with the official ElevenLabs API (https://api.elevenlabs.io) to perform administrative tasks, including reading branch states and version information.
- [COMMAND_EXECUTION]: Employs curl commands to execute operations on the ElevenLabs platform, such as fetching agent details, creating branches, and merging configurations.
- [DATA_EXPOSURE]: Uses an API key managed through the $API_KEY environment variable for authentication with vendor services, which is a standard security practice.
- [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill handles user-provided inputs such as branch names and descriptions as described in SKILL.md.
- Boundary markers: There are no specific delimiters or boundary markers mentioned for separating user input from system instructions.
- Capability inventory: The skill has the capability to perform network requests (curl) to modify agent configurations and traffic splits via the ElevenLabs API.
- Sanitization: No explicit sanitization or validation logic for user-supplied branch metadata is defined in the instructions.
Audit Metadata