skills/crazynomad/skills/flow-media/Gen Agent Trust Hub

flow-media

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides legitimate functionality for interfacing with Google Flow media generation tools. No malicious intent or behaviors were identified during the analysis.
  • [COMMAND_EXECUTION]: The skill uses shell scripts (scripts/veo-gen) to wrap the gflow-cli tool. These commands are necessary for the skill's core purpose and are implemented with appropriate error handling and retry logic.
  • [EXTERNAL_DOWNLOADS]: The skill documentation guides the user to install the gflow-cli package from PyPI using uv. It references a well-known university mirror for package downloads, which is a standard practice and does not involve untrusted sources.
  • [CREDENTIALS_UNSAFE]: The script scripts/session-probe accesses the browser cookie database associated with the tool's own profile to check for the presence and expiration of session tokens. This is used for diagnostic purposes to troubleshoot authentication issues and does not exfiltrate or print the actual secret values of the cookies.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 11:26 PM
Security Audit — agent-trust-hub — flow-media