weekly-digests — 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

  This skill generates narrative digests of project history by reading data from a local worker and using dynamic script generation to process it. It orchestrates subagents which process historical user prompts, creating a surface for indirect prompt injection. It also executes shell commands and inline JavaScript to manage its environment and configuration.

  Risk: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTIONJun 12, 2026Full report

• Socket

  pass

  No alerts

  Jun 12, 2026Full report

• Snyk

  warn

  Risk: MEDIUM · 2 issues

  Risk: MEDIUMJun 12, 2026Full report