editor-overlay

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill correctly implements credential management using the VIDJUTSU_API_KEY environment variable.\n- [DATA_EXFILTRATION]: The skill communicates with api.vidjutsu.ai to perform video processing. This network activity is documented and essential to the skill's core functionality. No sensitive local files or environment data are accessed or transmitted.\n- [PROMPT_INJECTION]: The skill ingests untrusted user data via the videoUrl and text parameters, creating a standard surface for indirect prompt injection. 1. Ingestion points: videoUrl and text fields in SKILL.md. 2. Boundary markers: None. 3. Capability inventory: Outbound HTTP POST requests. 4. Sanitization: None documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 01:53 AM