- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add code-yeongyu/oh-my-openagent --skill security-research -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add code-yeongyu/oh-my-openagent --skill security-research -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add code-yeongyu/oh-my-openagent --skill security-research -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add code-yeongyu/oh-my-openagent --skill security-research -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/code-yeongyu/oh-my-openagent/tree/HEAD/.agents/skills/security-research來自發布者
Use this skill to run a parallel security audit that separates real exploitability from generic concern. The team has 3 vulnerability hunters and 2 PoC engineers.
Before starting, verify:
team_* tools are available. If not, stop and tell the user:
security-research requires team-mode. Set team_mode.enabled: true in your oh-my-openagent config, restart opencode, then retry.If the user provided no target, audit the current repository and current branch diff against its upstream or merge base. If there is no diff, audit the security-sensitive surfaces in the working tree.
Use these references as the scoring frame:
Rules:
Create one Team Mode run with these 5 members:
Call team_create with an inline spec:
team_create({
inline_spec: {
name: "security-research",
description: "Parallel exploitability-driven security research team.",
members: [
{
name: "surface-hunter",
kind: "category",
category: "deep-low",
prompt: "You map attack surface. Enumerate entry points, trust boundaries, attacker-controlled inputs, data sinks, privilege transitions, and sensitive assets. Return evidence with file paths and exact functions. Do not assign severity unless you can name an attack path."
},
{
name: "auth-data-hunter",
kind: "category",
category: "ultrabrain",
prompt: "You hunt auth, authorization, tenant/data isolation, injection, SSRF, credential exposure, and confused-deputy flaws. Reason from attacker capability to impact. Return only findings with concrete exploit preconditions, CWE candidates, and verification steps."
},
{
name: "runtime-supply-hunter",
kind: "category",
category: "unspecified-high",
prompt: "You hunt filesystem, subprocess, archive extraction, dependency, hook execution, MCP, config, and environment-variable risks. Check path traversal, command injection, unsafe downloads, permission boundaries, and supply-chain assumptions. Cite file paths and commands used."
},
{
name: "poc-engineer-a",
kind: "category",
category: "unspecified-high",
prompt: "You build minimal safe PoCs for candidate findings. Use toy inputs and local-only execution. Your job is to prove or disprove exploitability, not to broaden scope. Report exact reproduction steps and expected output."
},
{
name: "poc-engineer-b",
kind: "category",
category: "deep-high",
prompt: "You independently reproduce candidate findings and try to falsify them. Downgrade anything without a working path. If a PoC is unsafe to run, design a safe static or dry-run proof and explain the limit."
}
]
}
})
If a category is unavailable, retry once by replacing only that category with unspecified-high. Do not reduce the team below 5 members.
Collect:
Use rg, git diff, git log, LSP, and existing tests before assigning work.
Send one prompt to the 3 hunters:
Audit target:
{target summary}
Context:
{diff, file list, security-sensitive paths, known constraints}
Task:
Find candidate vulnerabilities in your assigned role. For each candidate include:
- title
- affected file/function
- attacker capability
- attack path
- impact
- CWE candidate
- exact evidence
- safe verification idea
Reject generic hardening advice. Return only candidates with a plausible path.
Wait for all hunters.
Deduplicate hunter candidates. Send the strongest candidates to both PoC engineers.
Each PoC engineer must return:
Send the PoC results back to all 5 members.
Ask every member:
Produce this report:
## Security Research Result
### Verdict
PASS | PASS WITH FINDINGS | BLOCK
### Scope
- Target:
- Base/diff:
- Commands run:
### Findings
| Severity | Title | CWE | Exploitability | Impact | PoC | Fix |
|----------|-------|-----|----------------|--------|-----|-----|
### Finding Details
For each finding:
- Evidence:
- Attack path:
- PoC:
- Severity rationale:
- Minimal fix:
- Regression check:
### Downgraded or Rejected Candidates
| Candidate | Reason |
|-----------|--------|
### Residual Risk
- What was not tested and why.
Team Mode security research skill. Orchestrates 3 vulnerability hunters and 2 PoC engineers to audit a codebase in parallel, prove exploitability, classify root causes, and calibrate severity by actua
---name: security-researchdescription: Team Mode security research skill. Orchestrates 3 vulnerability hunters and 2 PoC engineers to audit a…---# .agents/skills/security-research/SKILL.md總覽
Team Mode security research skill. Orchestrates 3 vulnerability hunters and 2 PoC engineers to audit a codebase in parallel, prove exploitability, classify root causes, and calibrate severity by actual exploitability. Use for security review, vulnerability research, exploitability audit, pre-release security check, threat model validation, and `/security-research`. Triggers: 'security-research', 'security research', 'security review', 'vulnerability audit', 'exploitability audit', '보안 리뷰', '취약점 감사'.
常見問題
從發布者下載 .agents/skills/security-research/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/code-yeongyu/oh-my-openagent。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。