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 agentmods add skills/unclecheng-li/deepsec/redteam-cve-validationnpx skills add Unclecheng-li/DeepSec --skill redteam-cve-validationgit 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-validation)<a href="https://agentmods.dev/skills/unclecheng-li/deepsec/redteam-cve-validation"><img src="https://agentmods.dev/badge/skills/unclecheng-li/deepsec/redteam-cve-validation.svg" alt="Measured on agentmods" 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 | $0.00042 | $0.00501 |
| Opus 5 | $0.00021 | $0.00251 |
| Sonnet 5 | $0.00008 | $0.00100 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
redteam-cve-validation 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 6d 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-validation — 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CVE Validation
Domain
Validate candidate CVEs against the current target evidence without assuming exploitability.
The module consumes cve_candidate_list, product/version evidence, service fingerprints, and scope data, then decides whether the CVE path is usable, patched, not applicable, or needs more recon.
Trigger
cve_candidate_list_ready
Feedback Gates
- Scope Gate: target and asset must be in the declared authorization boundary.
- Evidence Gate: candidate CVE must map to observed product, version, endpoint, service, or fingerprint evidence.
- Applicability Gate: version range, configuration, and reachable component must plausibly match.
- Patch Gate: observed version or vendor advisory must not prove the issue fixed.
- Execution Gate: active validation requires a registered scoped adapter; missing adapters block rather than pretending execution happened.
Boundaries
- Do not run destructive or broad exploit attempts.
- Do not validate outside the declared target and scope.
- Do not treat CVE names alone as proof.
- Prefer passive or low-noise confirmation first.
- If evidence is insufficient, return to recon or CVE lookup rather than guessing.
Pivot Hints
- Candidate has no product/version match -> return to recon-intake for better fingerprinting.
- Candidate is patched or not applicable -> route by highest-ranked attack surface from recon.
- Tool or adapter missing -> record missing capability and request/choose an equivalent adapter.
- Too many candidates -> rank by reachable component, confidence, impact, and version fit.
Exit Conditions
- Confirmed applicable candidate -> continue to the specific validation/testing skill.
- All candidates patched/not applicable -> exit to evidence-based router.
- Evidence incomplete -> return to recon-intake or cve-lookup.
- Required tool/scope/adapter missing -> block with the missing capability or scope evidence.
Exit Evidence
- Required: cve_validation_result
- Optional: cve_patch_status, applicability_proof, non_applicability_reason
- min_attempts: 1
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.
- 6d ago First seen · 62 lines · 42 tokens per session scan A f00a98838e9a
redteam-cve-validation is a skill published in the GitHub repository Unclecheng-li/DeepSec (395 stars, last pushed 12d ago), licensed MIT. It adds 42 tokens to every session and 501 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to redteam-cve-validation, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
final-report
Final engagement report generation — executive summary, technical report, findings aggregation, attack path narrative, detection gap matrix, remediation roadmap.
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…
cve
Known CVE exploitation — fingerprint CMS/framework/plugin version, look up CVE candidates via cvelookup, retrieve PoCs via cvepoclookup, adapt the public exploit to the target, and confirm RCE. Use whenever the challenge tag is cve, recon fingerprinted a versioned service, or the challenge name hints at known…