← back to orchestrating-llm-attacks-with-pyrit

SkillMD Review · orchestrating-llm-attacks-with-pyrit

our safety review · skill by mukul975

CAUTION

Executes scripts that perform adversarial attacks against LLMs; requires API keys and network calls to external models.

reviewed 2026-07-06

What the verdicts mean

PASS

No risky instructions — documentation or standard, read-only development-tool usage.

CAUTIONthis skill

Legitimate purpose with real capabilities (runs scripts, calls services, or handles credentials). Read the skill before installing.

WARNING

Risky patterns beyond the skill's job — elevated privileges, config changes, or bypassed confirmations. Review carefully.

FAIL

Instructions a safe skill should never contain — injection, exfiltration, or destructive commands. Don't install unless you've verified the source.

INCONCLUSIVE

Could not be confidently assessed — treat as unreviewed and inspect the SKILL.md yourself.