eachlabs-video-edit
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill accepts untrusted data through parameters like video_url, audio_url, and prompt across model schemas in SKILL.md and references/MODELS.md.
- Ingestion points: External data enters the agent context via the input object in prediction requests.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore embedded commands within the processed URLs or prompts.
- Capability inventory: The skill's primary capabilities involve network operations (API calls) to api.eachlabs.ai; no sensitive local file access or arbitrary command execution is permitted.
- Sanitization: No input validation or content sanitization is documented within the skill files.
- [COMMAND_EXECUTION]: SKILL.md includes curl command templates used for demonstrating interaction with the EachLabs API. These examples are documented for instructional purposes and do not execute arbitrary user-controlled code on the local system.
Audit Metadata