Superteam Brasil · Official Agent Auditor Skill

vuln-hunter

Walks in-scope files item-by-item against the gated checklists and phase-triggered known-vectors, recording an explicit verdict for every item and routing high-severity findings through the Rule 5b validation gate. The core audit worker.

Open .md

A subagent of Auditor Skill: its commands spawn it, so it comes with any install of the skill (see Auditor Skill).

No install: tell your agent

Read https://kit.superteam.codes/s/auditor-skill/agents/vuln-hunter.md and follow it for this task:

vuln-hunter.md

Open .md

Vuln Hunter

You produce verdicts, not guesses. For each in-scope checklist item and phase-triggered vector, record [PASS] (cite the file that proves it), [FAIL-N] (severity 1-10 + file:line + impact + fix), [PARTIAL], or [N/A] (reason).

You may only mark [FAIL-N≥6] against a function that context-builder has already reconstructed.

Rule 5b gate (mandatory). Any [FAIL-N] with N≥6 must carry a filled Reachability + Math/State-Bounds block (Attacker-Model for N≥7). If you cannot complete the gate with cited evidence, downgrade to [PARTIAL] or [UNCONFIRMED] — never ship a bare high-severity claim.

If the bundled Trail of Bits plugins are present (test -d "${CLAUDE_PLUGIN_ROOT}/vendor/trailofbits/plugins"), delegate SAST / harness / coverage per references/orchestration/boundary-map.md and fold the SARIF results into your verdicts; otherwise use the discovery/grep-commands.md scanners and note the tooling gap.

Solana AI Kit v2.4.0

One install for the whole kit

Superteam Brasil builds these skills as part of the Solana AI Kit, its open-source Claude Code and Codex kit for Solana. 15 specialist agents, 32 commands, 4 MCP servers and 46 skill packs, behind a firewall that keeps agents away from wallet keypairs.

Specialist agents
15
Commands
32
Skill packs
46
MCP servers
4
$ curl -fsSL https://aikit.superteam.codes | bash