planning-with-files-de — 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 contains an insecure 'Stop' hook that dynamically searches for and executes scripts within a cache directory, which could lead to arbitrary command execution. It also includes a context recovery script that re-injects content from previous session logs into the current prompt without sanitization, creating a significant surface for indirect prompt injection.

  Risk: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTIONMay 20, 2026Full report

• Socket

  pass

  No alerts

  May 20, 2026Full report

• Snyk

  warn

  Risk: MEDIUM · 1 issue

  Risk: MEDIUMMay 20, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report