embedded-captions — security audits

Review recommended

Independent security partners scan this skill's files for malicious content, prompt injection and risky patterns. Verdicts below come from the skills.sh audit program; each partner links to its full report.

• Gen Agent Trust Hub

  warn

  The skill is functional for video captioning but includes a feature that executes arbitrary shell scripts from the project directory, which requires caution when handling untrusted data. It also performs runtime code execution for transcription and model weight downloads.

  Risk: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTIONJun 26, 2026Full report

• Socket

  warn

  2 alerts: gptSecurity, gptAnomaly

  Jun 26, 2026Full report

• Snyk

  warn

  Risk: MEDIUM · 1 issue

  Risk: MEDIUMJun 26, 2026Full report