Make Crazy Look

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses legitimate API endpoints (api.agent-media.ai) for its core functionality and adheres to its stated purpose of media creation.
  • [DATA_EXPOSURE]: Authentication is managed through the environment variable $AGENT_MEDIA_API_KEY. This follows best practices for secret management and avoids hardcoding sensitive credentials.
  • [COMMAND_EXECUTION]: The file mentions project-related scripts (e.g., scripts/generate-public-skill.ts) and directory structures, which are intended for skill maintenance and documentation rather than runtime execution of unauthorized shell commands.
  • [INDIRECT_PROMPT_INJECTION]: The caption input is a potential surface for untrusted data, but because it is rendered as static text on a video clip and not used to influence agent logic or system calls, it poses minimal security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 05:36 PM
Security Audit — agent-trust-hub — Make Crazy Look