redteam-selfattack@1.0.0
VERIFIED· install onlyPublisher claims: "红队自我攻防：给定目标策略，从已知攻击模板（提示注入/jailbreak角色扮演/编码混淆/ OOD/歧义）生成对抗探针，每条带红队 ground-truth，跑目标策略统计翻转率与盲区，输出 鲁棒分与盲区清单。让智能体主动生成对抗样本、自己测自己、自己暴露盲区——一线大模型 不具备的元治理能力，是"可靠地超越"的安全收口层。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-09 and scored it 93/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
Risk: Known attack templates do not cover all unknown or novel jailbreak techniques.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.红队自我攻防：给定目标策略，从已知攻击模板（提示注入/jailbreak角色扮演/编码混淆/Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.