BC ai-security-redteam
AI 安全与红队测试实操手册——覆盖 AI 系统六大攻击面（提示注入、越权与工具滥用、数据与隐私泄露、幻觉与质量缺陷、供应链与模型投毒、拒绝服务），OWASP LLM Top 10 风险映射，完整红队测试流程（目标定义/攻击面建模/用例设计/执行/报告/修复复测），直接与间接提示注入测试用例库、Agent 越权与沙箱逃逸测试、训练数据泄露与记忆攻击测试、幻觉检测基准，附漏洞分级与修复建议、零依赖本地工具一键生成风险清单、测试用例与报告模板。面向 AI 工程、安全测试、信息安全负责人，与 AI 治理/智能体治理形成"制度+技术"闭环。
AI 安全与红队测试实操手册——覆盖 AI 系统六大攻击面（提示注入、越权与工具滥用、数据与隐私泄露、幻觉与质量缺陷、供应链与模型投毒、拒绝服务），OWASP LLM Top 10 风险映射，完整红队测试流程（目标定义/攻击面建模/用例设计/执行/报告/修复复测），直接与间接提示注入测试用例库、Agent…
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 2
✓ No critical or high findings
Medium and low: 2
-
low Risky intent
intent-offensive-securitySKILL.md:17Offensive-security / dual-use content (legitimate for authorised testing; review intended use)description_en: A hands-on playbook for AI security and red team testing — covering six attack surfaces of AI systems (prompt injection, overreach and tool misuse, data and privacy leakage, hallucinat
-
low Risky intent
intent-offensive-securitySKILL.md:27Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Red Teaming
Files scanned: 19. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 269 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
description-no-whenneither description nor a "## When to Use" section says when to use the skill - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "display_name" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "title" - note
frontmatter-keyunknown frontmatter key "description_en"
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 603 tokens
- 100Running it twice. No mutating operations
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 269: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (9 of 9)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.