prompt-preflight-qa

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a robust framework for creative project management, aligning with its stated purpose of reviewing prompts and managing assets within a structured workspace.
  • [COMMAND_EXECUTION]: The skill utilizes standard system utilities including ffmpeg for generating placeholder media and yt-dlp for downloading video assets from manifest-defined URLs. These operations are performed as part of the project asset management lifecycle.
  • [EXTERNAL_DOWNLOADS]: Video content is fetched from remote URLs provided in project manifests. These downloads are handled as data assets for the project and do not involve executable code.
  • [CREDENTIALS_UNSAFE]: Authentication is managed by reading and writing session tokens to a local configuration file in the user's standard application configuration directory (e.g., ~/.config/postplus). No hardcoded secrets were detected in the source code.
  • [DATA_EXFILTRATION]: Network communication is directed to the vendor's infrastructure for session management, billing, and hosted media generation. All requests are authenticated and performed over secure protocols.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 07:44 AM
Security Audit — agent-trust-hub — prompt-preflight-qa