bx33661
UserEvidence-first vulnerability research workspace and Skills for Claude Code and Codex.
Categories
Indexed Skills (10)
omv-audit
Deep-audits a candidate finding from an Evidence.v1 file. Use when the user has an omv-find result they want to investigate further, wants to prove or disprove a vulnerability, needs to fill Evidence.v1 fields for omv-report, or invokes `/omv-audit`. Reads .omv/findings/<id>.yaml and produces a confirmed or blocked finding with all required evidence fields populated.
omv-find
Finds and ranks open-source packages worth auditing for passive CVE/VulDB research. Use when the user asks for vulnerability research targets, CVE hunting candidates, packages to audit, projects to fuzz, or `/omv-find`. Supports npm, Python, Go, Rust, Java, Ruby, PHP, C#, Swift, Dart, Elixir, Perl, R, and Lua, with strongest guidance for npm/Python/Go/Rust/Java/Ruby. Produces evidence-backed source -> sink -> guard notes, metadata, scoring, and local audit next steps without live exploitation.
omv-report
Generate a complete, ready-to-submit VulDB vulnerability report and CVE request. Covers all major package ecosystems: npm, pip, Go, Cargo (Rust), RubyGems, Maven, Gradle, NuGet, Composer (PHP), CocoaPods, Swift Package Manager, pub (Dart/Flutter), Hex (Elixir), CPAN (Perl), CRAN (R), LuaRocks. Use this skill whenever the user wants to submit a vulnerability to VulDB, request a CVE, write a security advisory, or document a security bug for disclosure. Trigger on phrases like submit to VulDB, request a CVE, write a CVE report, help me report this vuln, 提交 VulDB, 申请 CVE, 帮我报这个漏洞. Also trigger proactively when the user has just finished analysing a vulnerability in any package ecosystem and asks what to do next.
omv-repro
Guides a researcher through local reproduction of a vulnerability finding. Use when the user has an omv-audit result with evidence.reproducer filled but evidence.observed_result still unknown, wants to confirm a finding by running it locally, or invokes `/omv-repro`. Reads .omv/findings/<id>.yaml and guides step-by-step execution, then writes the observed result, records repro artifacts, and validates submission readiness.
omv
oh-my-vul local-first vulnerability research project manager for Pi, Codex, and Claude Code. Shows workspace status, next actions, installed omv-* skills, registry info, and delegates .omv findings lifecycle commands. Use when the user invokes /skill:omv, $omv, or /omv; asks what to do next; or manages local findings.
using-omv
Bootstrap discipline for oh-my-vul research. Use at the start of any vulnerability research conversation, when the user asks to audit/find/report a package, dig for CVEs, or run omv skills — and before claiming a finding is confirmed, ready to submit, or “done”. Establishes mandatory process, hard gates, and evidence-before-claims rules. Prefer this over improvising a research workflow.
omv-critic
Performs adversarial pre-submission review of an Evidence.v1 finding plus optional ThreatMap.v1 and Verification.v1 sidecars. Use before `/omv-report` when the user wants likely CNA rejection reasons, report argument quality review, or a reject_risk rating.
omv-dedup
Checks whether an Evidence.v1 finding is likely already disclosed. Use when the user asks to deduplicate a finding, check CNA duplicate risk, search NVD/GHSA/OSV/ecosystem advisory databases, or invokes `/omv-dedup`. Produces deterministic advisory queries and writes Evidence.v1 dedup fields only after confirmation.
omv-disclose
Helps prepare responsible disclosure communications and timelines from an Evidence.v1 finding. Use when the user asks to contact a vendor, create initial/follow-up/deadline disclosure email templates, plan a 90-day timeline, record disclosure fields, or invokes `/omv-disclose`.
omv-radar
Provides passive watchlist intelligence for oh-my-vul. Use when the user asks what changed for watched packages, ecosystems, vulnerability classes, advisories, releases, or invokes `/omv-radar`. Reads `.omv/radar/watchlist.yaml`, uses only passive external sources or offline fixtures, and writes local radar events for later briefings.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.