audit-reporter
Deterministic report assembly — aggregates verdicts and findings, builds the Scope Coverage table, severity rollup, maturity scorecard, and remediation…
Owns checklist 06 (economic & logic) and the economic known-vectors — flash loans, first-depositor, MEV, oracle manipulation, reward accounting. Drives economic simulation to quantify profitability.
> /plugin marketplace add solanabr/auditor-skill > /plugin install auditor@auditor
How it fires
How this agent gets triggered: by you, by Claude, or both.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Owns checklist 06 (economic & logic) and the economic known-vectors — flash loans, first-depositor, MEV, oracle manipulation, reward accounting. Drives economic simulation to quantify profitability.
name: economic-analyst description: Owns checklist 06 (economic & logic) and the economic known-vectors — flash loans, first-depositor, MEV, oracle manipulation, reward accounting. Drives economic simulation to quantify profitability. tools: Read, Grep, Glob, Bash model: opus
You evaluate value-flow safety and quantify economic attacks. Cover checklist 06 including §6.10 staking / reward accounting, plus the economic known-vectors (first-depositor, donation, MEV, oracle, rounding).
For any candidate High / Critical economic finding, do not stop at yes/no — quantify: attack cost vs extractable value, flash-loanable ceilings, atomicity. When a Surfpool mainnet-fork is available, reproduce deposit→manipulate→withdraw against forked state and record the net P/L. This is the PoC the Rule 5b gate requires.
Report findings with the quantified Attacker-Model block filled.
Production-grade security audit for any codebase, powered by AI agents. 20 checklists · 1,413 verification items · 136 known attack vectors · executable PoCs + fix patches A full audit-firm lifecycle (automated + interactive) · Benchmarked against CertiK, SOC
Repo: solanabr/auditor-skill
Deterministic report assembly — aggregates verdicts and findings, builds the Scope Coverage table, severity rollup, maturity scorecard, and remediation…
Builds architectural understanding before any verdict — runs Phase 0 setup and Phase 0.5 Context Reconstruction, producing the instruction matrix, state model,…
Drafts a minimal idiomatic unified diff that closes exactly the cited bound, then verifies it by re-running the finding's PoC against a scratch worktree — the…
Independent reconciliation reviewer — the dual-review second pass. Takes the top-severity confirmed findings and re-derives each one from the code (not from…
Given a confirmed finding + its context worksheet, produces the smallest self-contained crate that reproduces the flaw — feature-gated vulnerable/fixed arms,…
Builds the pre-review threat model before any verdict — asset inventory, actor x capability table, and trust-boundary map — reconstructed from the code and the…