eachlabs-face-swap
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external image and video URLs, as well as text prompts, which are provided by the user or external data sources.
- Ingestion points: The target_image, swap_image, target_video, and prompt input parameters defined in the API request examples.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore instructions potentially embedded in the processed data.
- Capability inventory: The skill utilizes network capabilities via curl to interact with the eachlabs.ai API.
- Sanitization: The skill relies on the EachLabs API service to process and sanitize the content within the input URLs and prompts.
Audit Metadata