reels-script

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Security analysis of the skill's instructions and reference files identifies no malicious patterns, command injection, or attempts to bypass platform safety guidelines.
  • [DATA_EXPOSURE]: The skill reads internal configuration files, specifically brand-profile.md and voice.md. These files are utilized for content personalization and do not involve unauthorized access to sensitive system credentials or private user data beyond what is required for the agent's function.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection through the ingestion of brand data and user-provided concepts. However, its capabilities are restricted to script generation and routing tasks to internal tools, resulting in a safe risk profile. 1. Ingestion points: brand-profile.md, voice.md, and user concepts (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Content generation and hand-offs to internal publishing skills. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 02:27 PM
Security Audit — agent-trust-hub — reels-script