ptn1411/skill/searching-exploit-db
Claude Code and agent skill by ptn1411/skill
- community
Checking that the SKILL.md file is still in the repository.
Use when looking up CVE identifiers, EDB-IDs, public exploit references, or product/version matches in Exploit-DB for vulnerability research or authorized security assessment.
Install
npx vskill@latest install ptn1411/skill/searching-exploit-dbSKILL.md
Searching Exploit-DB
Purpose
Find public Exploit-DB entries reproducibly, then assess whether each entry is relevant to the user's product and environment. An Exploit-DB match proves that a public PoC exists; it does not prove that a target is vulnerable or that the PoC is safe to run.
Workflow
Use the bundled read-only helper on Windows or when searchsploit is unavailable:
The helper reads the official files_exploits.csv from the Exploit-DB GitLab repository. Pass --csv <path> to use a local clone or saved CSV. On systems with SearchSploit, searchsploit --cve 2021-44228 -j is also appropriate.
For screenshots, tags, setup files, and vulnerability mappings absent from the CSV, inspect the corresponding https://www.exploit-db.com/exploits/<EDB-ID> page.
Assess Applicability
For every candidate:
- Confirm the CVE and affected versions with the current vendor advisory, CVE record, or NVD; recommend the vendor's current supported remediation, not merely the first historical fixed release.
- Compare product, exact version, architecture, attack type, prerequisites, authentication, and network position. Distinguish the vulnerable target OS, the PoC's supported target platform, and the host used to run the PoC.
- Report Exploit-DB's
verifiedvalue without treating it as a guarantee. - State missing facts and distinguish
direct match,possibly relevant, andnot applicable.
Do not download, compile, or execute a PoC as part of lookup. If the user asks to test one, confirm the target is owned or explicitly authorized and use the appropriate assessment skill.
Outputs
Return:
| Field | Content | |
|---|---|---|
| Query | Normalized CVE, EDB-ID, or terms | |
| Matches | EDB-ID, title, platform/type, date, verified status, URL | |
| Applicability | Direct, possible, or not applicable with reasons | |
| Validation | Linked Exploit-DB page plus vendor/CVE advisory and affected-version evidence | |
| Caveats | Preconditions, missing evidence, and safe next step |
Include the CSV source and retrieval time so a changing main branch result can be traced.
If there is no match, say that Exploit-DB has no indexed result; do not claim that no public exploit exists elsewhere.
Anti-Patterns
- Matching a CVE by substring instead of the exact
codestoken. - Treating an EDB entry as authoritative affected-version data.
- Selecting a PoC by title while ignoring platform or prerequisites.
- Equating
Not verifiedwith false, orVerifiedwith universally reliable.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingsearching-exploit-db/SKILL.md
Popularity
- Repository stars
- 150
- Repository forks
- 90
- 7-day trend score
- 25
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/ptn1411/skill/searching-exploit-db)