video-ad-specs

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes multiple Bash examples using the infsh CLI (the author's own tool). These commands are used to log in, run AI video generation models (from ByteDance, Google, and Fal.ai), and perform video editing tasks like merging audio or adding captions. All tools and references are consistent with the 'inference-shell' vendor context and represent the primary functionality of the skill.
  • [EXTERNAL_DOWNLOADS]: The skill mentions installation instructions for the vendor's tools via npx skills add inference-sh/skills@agent-tools. These are references to the vendor's own official packages and are considered safe as they align with the skill's purpose and author identity.
  • [SAFE]: No malicious prompt injection, data exfiltration, obfuscation, or persistence mechanisms were detected. The technical specifications and ad-creation frameworks provided are informational and present no security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 09:27 PM