longform-to-shorts

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a workflow for transforming long-form creator content into short-form assets like TikToks or Reels. Analysis of the instructions and references shows no evidence of malicious patterns.
  • [NO_CODE]: The skill does not include any scripts (Python, JavaScript, shell) or external dependencies. It relies purely on the AI's natural language processing capabilities to follow the provided checklist.
  • [DATA_EXPOSURE]: There are no hardcoded credentials, API keys, or attempts to access sensitive system files like SSH keys or environment variables.
  • [PROMPT_INJECTION]: The instructions do not contain any bypass attempts, role-play injections (DAN), or commands to ignore previous safety guidelines.
  • [INDIRECT_PROMPT_INJECTION]: While the skill is designed to process untrusted data (external blogs, newsletters, etc.), it lacks the high-risk capabilities (like file writing or network requests) that would make it a target for exploitation. The risk is limited to content accuracy which is addressed in the safety rules.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 05:07 PM
Security Audit — agent-trust-hub — longform-to-shorts