Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Unclecheng-li/DeepSec --skill redteam-cve-lookupgit clone --depth 1 https://github.com/Unclecheng-li/DeepSecWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/unclecheng-li/deepsec/redteam-cve-lookup)<a href="https://agentmods.dev/skills/unclecheng-li/deepsec/redteam-cve-lookup"><img src="https://agentmods.dev/badge/skills/unclecheng-li/deepsec/redteam-cve-lookup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/unclecheng-li/deepsec/redteam-cve-lookup"><img src="https://agentmods.dev/badge/skills/unclecheng-li/deepsec/redteam-cve-lookup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.00801 |
| Opus 5.5 | $0.00017 | $0.00320 |
| Sonnet 5.5 | $0.00009 | $0.00160 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
redteam-cve-lookup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to redteam-cve-lookup — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
CVE Lookup
Domain
Recon Profile 完成后的 CVE 匹配与适用性评估阶段。 根据已收集的产品名、版本号、服务指纹，查询已知 CVE，评估其对目标的适用性。
阶段顺序：
- 从 recon_profile 提取产品/版本/服务清单
- 按产品+版本查询 CVE 数据库(NVD/CVE MCP/本地库)
- 初筛：排除明确不匹配的 CVE(产品不符/版本范围外)
- 适用性评估：结合目标指纹判断 candidate/possibly_applicable/not_applicable/patched
- 补丁状态确认：检查已部署版本是否包含修复
Trigger
recon_profile_ready
Feedback Gates
- Product Gate：recon_profile 中是否存在可识别的组件/产品名。无产品名则证据不足，回退 recon 补证。
- Version Gate：是否有版本号或可比对的指纹信息。无版本信息降低 confidence 但不阻断。
- Source Gate：CVE 来源是否可追溯(NVD/MITRE/厂商公告)。不可追溯标记 low confidence。
- Applicability Gate：是否有证据证明目标适用该 CVE。无证据标记 candidate 待验证。
- Patch Gate：是否有证据表明已修复(版本号高于修复版本/补丁已部署)。已修复标记 patched。
Boundaries
- 不执行任何漏洞利用或 PoC
- 不发送攻击性 payload 验证 CVE
- 仅查询当前目标，不自动扩展到任务中未出现的关联目标
- CVE 查询阶段只做信息匹配，不做主动验证
- 对低置信度候选不做过度推断
- 遵循最小请求原则，避免批量爬取 CVE 数据源
Pivot Hints
- 产品名不明确 → 回退 recon，尝试更精确的指纹识别(Wappalyzer/httpx tech detect)
- 版本号缺失 → 尝试从 HTTP header/error page/changelog 推断版本范围
- CVE 数据源不可用 → 降级到离线 CVE 字典或已知漏洞列表
- 候选过多(>20) → 按 CVSS 评分+影响范围排序，优先评估高危+RCE类
- 全部标记 patched → 输出 cve_patch_status artifact，退出到 evidence-based router
- 无任何候选 → 输出空 cve_candidate_list，退出到 evidence-based router
Exit Conditions
- 存在 possibly_applicable 或 candidate CVE（confidence >= medium）→ 进入 cve-validation path
- 全部 CVE 标记 not_applicable 或 patched → 退出到 evidence-based router
- 产品/版本证据不足，无法生成有效候选 → 回退 recon-intake 补证
- 无 CVE 候选（产品无已知漏洞）→ 退出到 evidence-based router
Exit Evidence
- Required: cve_candidate_list
- Optional: cve_applicability_matrix, cve_patch_status
- min_attempts: 2
Capabilities
cve_lookup -> cve_candidate_list
cve_applicability -> cve_applicability_matrix
patch_status_check -> cve_patch_status
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 72 lines · 43 tokens per session scan A d2779f8974ca
redteam-cve-lookup is a skill published in the GitHub repository Unclecheng-li/DeepSec (498 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 801 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to redteam-cve-lookup, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
ti-yara-hunting
YARA rule writing from behavioral observations and TI report analysis — sample-to-rule conversion, condition optimization, performance tuning, and retrohunting on VirusTotal and ANY.RUN. Covers YARA/YARA-X syntax, yarGen automated generation, and production rule deployment.
exploit-reporting
Exploitation finding documentation — initial access reports, exploit chain documentation, CVSS v4.0 scoring, shell/credential inventory, detection gap analysis.
ti-ioc-extraction
Automated IOC extraction from threat reports, logs, and unstructured text — parse hashes, IPs, domains, URLs, email addresses, and CVEs. Covers regex-based extraction, defanging/refanging, bulk hash lookup, IOC deduplication, YARA rule generation from IOCs, and STIX/TAXII formatting for sharing.
m365-mailbox-compromise
Microsoft 365 mailbox compromise chain — OAuth consent phishing, delegate access abuse, mail rule persistence, and token theft via device code phishing. Full kill chain from initial access to persistent email collection.
web
Web application exploitation — the primary category skill for all web-based attacks. This is a routing skill: read this first to identify the attack type, then load the appropriate specialized sub-skill for detailed procedures. Covers 11 technique areas across injection, file access, authentication, and API…
pentest-task-tree
Iterative PTT (Penetration Testing Tree) session reasoning — build, update, and traverse a live numbered task tree to drive LLM-guided pentest decisions across a full session.