writing-video-scripts

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions for creative writing and content formatting. There are no executable scripts, shell commands, or network operations present in the files.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided script briefs. While this represents a surface for indirect prompt injection, the skill's lack of system capabilities (e.g., file writing, network access, or command execution) prevents these inputs from being leveraged for malicious actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 05:34 PM
Security Audit — agent-trust-hub — writing-video-scripts