ai-research-explore — 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 facilitates deep learning research by orchestrating experiments, generating ideas, and fetching reference metadata. It performs dynamic execution of Python code from the local research repository to verify implementation feasibility and runs arbitrary shell commands specified in configuration files. It also fetches data from trusted sources like arXiv, DOI, and GitHub, presenting a surface for indirect prompt injection.

  Risk: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTIONDATA_EXFILTRATIONJul 27, 2026Full report

• Socket

  warn

  2 alerts: gptSecurity, gptAnomaly

  Jul 27, 2026Full report

• Snyk

  warn

  Risk: MEDIUM · 1 issue

  Risk: MEDIUMJul 27, 2026Full report