Security Watch — Security skill for Claude Code
One security-watch pass over an EVM / Solidity repo — deps + static analysis + risky-pattern grep + recent advisories → a dated report.
How to install Security Watch
Installs to ~/.claude/skills/oxtof-evm-security-watch-security-watch/SKILL.md
mkdir -p ~/.claude/skills/oxtof-evm-security-watch-security-watch && curl -fsSL https://raw.githubusercontent.com/OxToF/evm-security-watch/HEAD/commands/security-watch.md -o ~/.claude/skills/oxtof-evm-security-watch-security-watch/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Security Watch does
description: One security-watch pass over an EVM / Solidity repo — deps + static analysis + risky-pattern grep + recent advisories → a dated report. Proposes fixes, never applies them. argument-hint: "[path-to-solidity-repo]"
/security-watch
Run one **watch pass** over the Solidity repo at `$ARGUMENTS` (default: current directory). Produce a dated report. **Propose, don't apply** — never patch production code.
**Verification discipline applies to every step below** — see [`skill/dai
Alternatives in Security
- Bountyforge — All-round bug bounty skill for Claude Code parallelized agents for smart contract audits (EVM, Move, Solana, T 399 ★
- Memory Self Review — Mine recent agent history (claude-mem + usage stats) for recurring failures and repeated patterns, audit MEMOR 297 ★
- Scv Scan — A Claude Code skill that scans Solidity codebases for security vulnerabilities by referencing 36 unique vulner 105 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Absorb
Maintainer-only: audit the kit's upstream sources (Credits drift + seed-rescan) and draft a dated, proposal-on
Arbitus
Open-source security gateway for MCP tool calls — blocks secret leaks, enforces agent policies, and requires h
Advisories
Triage and clear known security advisories by reachability — batched so a break is attributable, nothing bundl
Rust Audit
Audit a Rust project against rustkb best practices — dependencies, advisories, lints, architecture, unsafe
LLM Filesystem Tools
Python filesystem tools for AI models and LLMs. Secure directory access, file reading, grep search for Ollama,
Audit Cpi
Checklist-driven CPI safety review — locates CPI sites with grep, walks skills/solana-cpi-safety/cpi-checklist
Related Agents
Tp Dep Health
PROACTIVELY use this when the user asks "which dependencies should I update", "any stale / risky packages", "a
Seed Analyst
tradefloor swarm seed analyst. Gathers the events that will move one instrument - news, results dates, filings
Fit Scorer
Scores every company on the target list against the buy box into PRIORITY, WATCH or PASS. Builds a written rub