video-background-removal
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 ingest and process external content from user-provided URLs which could potentially contain malicious instructions. * Ingestion points: video_urls, image_urls, and user messages in API request examples in SKILL.md. * Boundary markers: None present in the provided examples to delimit user content from system instructions. * Capability inventory: The skill performs network requests (POST) to the eachlabs API endpoint (eachsense-agent.core.eachlabs.run). * Sanitization: No specific sanitization, validation, or filtering of the remote content is described in the documentation.
- [SAFE]: Authentication is handled correctly using environment variable placeholders ($EACHLABS_API_KEY) in the example curl commands, following secret management best practices.
- [SAFE]: All network operations and references are directed to infrastructure belonging to the skill author (eachlabs.run and eachlabs.ai), representing legitimate vendor functionality.
Audit Metadata