hypogenic — 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

  pass

  This skill facilitates automated scientific hypothesis generation and testing by processing empirical datasets and research literature. It requires installing the 'hypogenic' Python package and cloning specialized datasets from the ChicagoHAI GitHub organization. The primary security consideration is the surface for indirect prompt injection, as the skill interpolates untrusted data from JSON files and PDFs into LLM prompts without explicit sanitization or boundary delimiters.

  Risk: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTIONApr 11, 2026Full report

• Socket

  pass

  No alerts

  Apr 11, 2026Full report

• Snyk

  warn

  Risk: MEDIUM · 2 issues

  Risk: MEDIUMApr 11, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 15, 2026Full report