Real Skill packageSource verifiedClawHub registry

agent-redteam-kit

当用户说『测一下这个AI安不安全』『会不会被越狱』『让AI干危险的事它听不听』『上线前做对抗测试』,或要给一个 agent/提示词做安全性红队时使用。中英双库扫描越狱/危险能力请求(DAN/忽略指令/提权/数据外泄/自改进等),给出风险分级+加固建议,并设「危险操作闸门」(有门禁)。可运行脚本(redteam_scan 扫描器)。理论根基:LGD 三律之有门禁(危险动作先过闸)。触发词:红队、red team、越狱、jailbreak、对抗测试、prompt攻击、AI安全测试、危险指令、安全评估。

Identity and source

Publisher attributionzhaoxinghua09-cellregistry owner unverified by skillvetai
Functional categoryWriting, Content & Translationautomatically inferred · 56% rule confidence
Package forminstruction with code8 recorded files
Canonical sourceClawHub registryclawhub:zhaoxinghua09-cell:agent-redteam-kit
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 10/17/2026.claude/skills/agent-redteam-kit

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 10/17/2026.agents/skills/agent-redteam-kit

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 10/17/2026skills/agent-redteam-kit

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @zhaoxinghua09-cell/agent-redteam-kit
clawhub inspect @zhaoxinghua09-cell/agent-redteam-kit --version 1.0.4

Security evidence

SkillVetAI static result: medium signal

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
6 / 8 inspected as text
Checked
10/17/2026, 4:22:39 AM
Scanner
0.1.3
Policy
1.0.3
1 automated finding
mediumPrompt-override language requires reviewscripts/redteam_scan.py:20 · confidence 62%print (the )?(system prompt
2 inferred permission indicators
  • network access — automatically inferred
  • filesystem read — automatically inferred
2 dependency and API indicators
  • api: clawhub.ai
  • api: github.com
External clawhub result: clean

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
10/17/2026, 12:33:24 AM
Release binding
Matches this record
  • vt: clean
  • skillspector: suspicious
  • llm: clean

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:7903e56b1dad89cafcddd3f13ac9893d1cac0aac47c9da3c0e6628761cfe9937
Show up to 8 recorded paths
  • AGENTS.md
  • icon.png
  • lgd-powered.png
  • llms.txt
  • README.md
  • scripts/redteam_scan.py
  • skill-card.md
  • SKILL.md

Source changelog

- Major update: Streamlined documentation, focused on bilingual security testing and usage. - Simplified and rewrote SKILL.md with clearer English-first and Chinese-after sections. - Added new files for agent info and assets, removed legacy and redundant markdown/docs. - Updated risk rationale and changelog fields; defined risk tier (medium) and safety/compliance stance. - Refined permissions and usage notes; reduced allowed tools to core read/edit actions. - Added concise usage instructions and clarified "when to use" scenarios for adversarial/red-team testing workflows.

Release security diff

mediumCompared fixed releases 1.0.3 and 1.0.4; 0 finding and 0 permission indicators were added.

Both fixed releases were scanned under the current scanner and policy, so finding, permission and dependency changes are available.

Change reasons and limitations
  • dependency surface changed
  • file surface changed
  • content hash changed

Observed release history

These older immutable releases were observed by prior successful syncs. They remain recorded when a newer release becomes current.

1.0.39/28/2026sha256:2815a0716bf1eab2af104624a3dd87a4ae5c7e25430e6a29fa178d03e843f719
1.0.09/11/2026sha256:4e6d7d8ba8c08bdbfa8bf24601af84cf679ac3f1a31c4ddd62bba91553ce855d