跳转到正文
报告库
用途分类 / 其他用途

Council Skill 安全审计

作者说它能做什么(原文)

Run a model-diverse subagent council to investigate the same problem from multiple perspectives, compare findings, and produce a final recommendation. Use this skill whenever the user asks for a council, second opinions, multiple agents/models to evaluate one question, parallel investigation, red-team/blue-team comparison, or help deciding between competing technical approaches.

第三方安全检查结论

发现安全风险

已检查文件
1
发现的风险
2
会不会运行危险命令?检查是否下载程序后直接运行、让他人远程控制电脑,或藏起要运行的命令。未发现风险
会不会泄露文件和密钥?检查是否发送含密码或密钥的文件,以及代码里是否直接写了密钥。发现 1 项风险
中风险

仓库和设计上下文可能被发送给多个模型提供方

原文依据:5 处
发现了什么

Skill 优先使用不同模型家族,并要求给子代理提供仓库路径、背景、相关文件或符号。某些候选模型可能由不同的远程提供方托管,因此同一份代码或设计信息可能跨多个服务处理。

为什么需要注意

如果提示中包含私有源代码、未公开设计、客户数据或凭据,这些内容可能进入多个提供方的处理或日志范围,扩大数据暴露面。

该 Skill 要求优先使用不同模型家族,并把仓库或制品位置、背景及相关文件/符号写入共享简报。因此,如果所选子代理由不同远程服务托管,同一项目上下文可能被多个提供方处理;源码并未说明这些模型一定是远程的,也未证明已发生传输。用户可要求只使用获准或本地模型,并限制简报中的代码、路径和敏感设计信息。

SKILL.md:29来自说明文档打开原文件
Preferred default roster for a three-member council:- Opus 4.7 or the strongest available Claude/Opus reasoning model: architecture, correctness, and edge-case analysis.- GPT 5.5 or the strongest available GPT/Codex model: implementation-grounded review, feasibility, and test strategy.- An open-source model such as Kimi 2.6, GLM 5.1, or the strongest available OSS/local model: contrarian critique, hidden assumptions, and alternative framing.If one of these exact models is unavailable in the active harness, use the closest available model from that family and note the substitution. If no open-source model is available, use a third distinct frontier model if possible; otherwise use the strongest remaining model with a deliberately adversarial or specialist angle.
查看另外 4 个位置
SKILL.md:54来自说明文档打开原文件
The shared brief should include:- repository path or artifact location;- current branch or base context;- the exact question to answer;- relevant background and known concerns;- required files/symbols to inspect, if known;- constraints, especially read-only/no commits/no PRs;- expected report format.
SKILL.md:52来自说明文档打开原文件
For explicit orchestration requests, briefly tell the user which council members you plan to launch and what each will investigate, then wait for approval before calling `run_agents`.
SKILL.md:27来自说明文档打开原文件
Prioritize model diversity. A council should not default to three agents on the same model with different angles; use that only when the available launch configuration cannot provide multiple useful models, or when the user explicitly asks for one model. If model diversity is unavailable, say so briefly before falling back to perspective-only diversity.
SKILL.md:31来自说明文档打开原文件
- Opus 4.7 or the strongest available Claude/Opus reasoning model: architecture, correctness, and edge-case analysis.- GPT 5.5 or the strongest available GPT/Codex model: implementation-grounded review, feasibility, and test strategy.- An open-source model such as Kimi 2.6, GLM 5.1, or the strongest available OSS/local model: contrarian critique, hidden assumptions, and alternative framing.
会不会删除文件或一直在后台运行?检查是否大范围删除文件、改写磁盘,或设置自动启动。未发现风险
会不会绕过安全保护?检查是否跳过网站安全验证、开放过多文件权限,或取消操作前的确认。未发现风险
会不会误导 AI 或隐藏内容?检查工作说明是否要求 AI 忽略你的指令、干扰检查结果,或夹带看不见的文字。未发现风险
会不会偷偷改推广链接或收款方?检查是否强制替换推广链接或收款对象,同时要求隐瞒更改。发现 1 项风险
中风险

一次普通的“第二意见”请求可能触发多次付费模型调用

原文依据:4 处
发现了什么

Skill 的触发范围包括第二意见和技术方案选择,默认委员会有三名成员;不同模型还需要分别调用 run_agents。只有“显式编排请求”明确要求启动前等待批准。

为什么需要注意

在按调用或按 token 计费的账户上,用户可能在未看到成员、模型和预算的情况下产生多次模型费用,并消耗并发或配额。

这段证据能说明什么

源码支持“第二意见”即可触发该 Skill、默认启动三名成员,并可能因模型不同产生多次独立调用;而且只有“显式编排请求”明确要求先获批准。这可能增加调用量或配额消耗。但源码没有价格、计费账户或各模型是否收费的信息,因此无法确认这些一定是“付费”调用。用户可要求作者在任何多代理启动前展示成员数量、模型、预计调用次数和费用并逐次确认。

这项判断针对展示的代码和适用条件,不表示风险已经实际发生。
SKILL.md:3来自说明文档打开原文件
name: councildescription: Run a model-diverse subagent council to investigate the same problem from multiple perspectives, compare findings, and produce a final recommendation. Use this skill whenever the user asks for a council, second opinions, multiple agents/models to evaluate one question, parallel investigation, red-team/blue-team comparison, or help deciding between competing technical approaches.---
查看另外 3 个位置
SKILL.md:29来自说明文档打开原文件
Preferred default roster for a three-member council:- Opus 4.7 or the strongest available Claude/Opus reasoning model: architecture, correctness, and edge-case analysis.- GPT 5.5 or the strongest available GPT/Codex model: implementation-grounded review, feasibility, and test strategy.- An open-source model such as Kimi 2.6, GLM 5.1, or the strongest available OSS/local model: contrarian critique, hidden assumptions, and alternative framing.
SKILL.md:44来自说明文档打开原文件
When different children need different models, launch them in separate `run_agents` calls because model selection is run-wide. If the requested model resolves differently than expected, treat the resolved launch settings as authoritative and continue unless they make the task infeasible.
SKILL.md:52来自说明文档打开原文件
For explicit orchestration requests, briefly tell the user which council members you plan to launch and what each will investigate, then wait for approval before calling `run_agents`.

Skill 逻辑拆解

3 个说明模块

该 Skill 会让多个子代理独立调查同一问题,再由主代理按证据质量汇总建议,而不是按票数决定。

查看原文
SKILL.md:8来自说明文档打开原文件
Use this skill to coordinate multiple subagents investigating the same question, with different models first and different assigned perspectives second, then synthesize their reports into one recommendation.This skill is best for judgment-heavy tasks: architecture tradeoffs, risky bug fixes, code review red-teaming, rollout decisions, incident analysis, and “is this alternative worth pursuing?” questions.
SKILL.md:88来自说明文档打开原文件
Compare the reports by evidence quality, not by vote count. In the final answer:- lead with the recommendation;- call out consensus and disagreements;- explain why the recommended option wins against the decision criteria;- explicitly address the user’s stated concern;- include relevant file paths/symbols without overloading the answer;- distinguish “do now” from optional future hardening;- mention confidence and material unknowns.

默认委员会包含三个不同模型家族,并为每个成员分配不同审查角度;如果模型不可用,Skill 会选择替代模型。

查看原文
SKILL.md:29来自说明文档打开原文件
Preferred default roster for a three-member council:- Opus 4.7 or the strongest available Claude/Opus reasoning model: architecture, correctness, and edge-case analysis.- GPT 5.5 or the strongest available GPT/Codex model: implementation-grounded review, feasibility, and test strategy.- An open-source model such as Kimi 2.6, GLM 5.1, or the strongest available OSS/local model: contrarian critique, hidden assumptions, and alternative framing.If one of these exact models is unavailable in the active harness, use the closest available model from that family and note the substitution. If no open-source model is available, use a third distinct frontier model if possible; otherwise use the strongest remaining model with a deliberately adversarial or specialist angle.

只读调查让所有子代理使用同一检出目录;实现或原型任务则要求为每个本地子代理建立独立 Git worktree 和分支。

查看原文
SKILL.md:48来自说明文档打开原文件
For read-only investigations, keep all children in the same checkout and explicitly tell them not to edit files. For implementation or prototyping councils, give each local child its own git worktree and branch so they cannot collide.
SKILL.md:127来自说明文档打开原文件
- If the council is read-only, tell children not to modify files, commit, create branches, or open PRs.- If the council involves PR or branch work, follow the repository’s normal version-control rules and use isolated worktrees for parallel local edits.- If the council is about code review feedback, mark review comments resolved only after the underlying issue is actually addressed.- Do not expose internal child agent IDs in user-facing summaries unless the user explicitly asks for them.

启动前的用户批准仅明确适用于“显式编排请求”;其他触发方式没有同样明确的逐次批准要求。

查看原文
SKILL.md:3来自说明文档打开原文件
name: councildescription: Run a model-diverse subagent council to investigate the same problem from multiple perspectives, compare findings, and produce a final recommendation. Use this skill whenever the user asks for a council, second opinions, multiple agents/models to evaluate one question, parallel investigation, red-team/blue-team comparison, or help deciding between competing technical approaches.---
SKILL.md:52来自说明文档打开原文件
For explicit orchestration requests, briefly tell the user which council members you plan to launch and what each will investigate, then wait for approval before calling `run_agents`.
从这里开始 · 工作说明SKILL.md
council
连线表示工作说明包含的模块,不是实际运行顺序。点击模块可查看原文。
文件与检查记录1 个文件

检查范围与遗漏

逐文件查看涉及的内容

下方列出本次涉及的原文范围;纳入检查不代表已查清所有问题。

  • SKILL.md已纳入全文

这份报告只针对上方版本。我们看了拿到的代码和说明文件,没有实际运行 Skill,也没有检查它另外安装的软件包。因此,这不是“保证安全”的承诺;换了版本或使用环境,结果也可能不同。

  • SKILL.md工作说明
读取了多少行
131
文件校验值(用于核对版本)
52b92bd892f98cf0de07a88ce880dc99c59d633b7253ecd3ac90c4fea1a0f799