Security Harness

Security Harness

A multi-agent application-security review harness for Claude Code (and, later, other AI agents). One
router skill dispatches to a full offensive-security pipeline that maps a codebase, hunts
vulnerabilities with a per-class knowledge base, chains findings into escalations, verifies real
impact, and reports to README / JSON / SARIF / doc / PDF.
Scope: this harness performs static analysis (source review, data-flow tracing, PoC/payload
construction) on code you own or are authorized to test. It does not attack live third-party systems.

What's inside

Vulnerability classes covered (the sh-kb-* skills)

access-control (IDOR/BOLA/priv-esc) · sqli · xss · ssrf · injection (cmd/code/SSTI/LDAP) · auth (session/JWT)
· deserialization · path-traversal (LFI/RFI) · secrets · csrf · xxe · open-redirect · crypto · race-conditions
· file-upload. Dependency CVEs/SBOM are handled by the recon stage.

Install

The harness ships for several agents. Full packaging details and the release
checklist are in docs/DISTRIBUTION.md.

Claude Code - add this repo as a plugin marketplace and install the plugin:

/plugin marketplace add accepts any of: a GitHub owner/repo (as above), a full git URL
(https://github.com/dmdhrumilmistry/security-harness.git), or a local path to a clone
(e.g. /plugin marketplace add ./security-harness from the directory containing your checkout).
Then run /plugin install security-harness and reload when prompted.

Gemini CLI - a native extension, manifest at the repo root:

opencode, Codex, or any agentskills.io agent - copy the
skills into a discovery directory. Codex additionally picks up AGENTS.md on its own:

Graft is installed and set up automatically by the pipeline. Stage 0 runs npm install -g
@nanonets/graft if it's missing (requires…