figure-generation — security audits

Flagged by auditors

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

  fail

  This skill implements a 'Generate-then-Execute' pipeline that creates and runs arbitrary Python code on the local system based on user-provided descriptions. This pattern is highly susceptible to prompt injection attacks where a malicious request could cause the agent to generate and execute code that deletes files, exfiltrates sensitive data, or installs malware.

  Risk: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTIONFeb 22, 2026Full report

• Socket

  pass

  No alerts

  Mar 18, 2026Full report

• Snyk

  pass

  Risk: LOW · No issues

  Risk: LOWFeb 22, 2026Full report

• Runlayer

  pass

  3/3 files flagged

  Risk: LOWFeb 23, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report