llm-prompt-injection — 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

  warn

  This skill is a security testing playbook for Large Language Models (LLMs), detailing methods for prompt injection and jailbreaking. While educational, it contains a high density of malicious payloads, including instructions to bypass safety guidelines, extract system prompts, and perform data exfiltration. The presence of these patterns could be misinterpreted by an AI agent, leading to unauthorized actions or compromise.

  Risk: MEDIUMPROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONREMOTE_CODE_EXECUTIONApr 9, 2026Full report

• Socket

  warn

  2 alerts: gptSecurity

  Apr 9, 2026Full report

• Snyk

  fail

  Risk: CRITICAL · 3 issues

  Risk: CRITICALApr 9, 2026Full report

• ZeroLeaks

  warn

  3 findings · Score: 69/100

  Risk: MEDIUMApr 16, 2026Full report