Chain Findings — Security skill for Claude Code
Escalate low-severity findings into reportable vulnerabilities by building exploit chains (A→B→C).
How to install Chain Findings
Installs to ~/.claude/skills/tyrusrc-praetor-chain-findings/SKILL.md
mkdir -p ~/.claude/skills/tyrusrc-praetor-chain-findings && curl -fsSL https://raw.githubusercontent.com/TyrusRC/praetor/HEAD/.claude/skills/chain-findings.md -o ~/.claude/skills/tyrusrc-praetor-chain-findings/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Chain Findings does
name: chain-findings description: Escalate low-severity findings into reportable vulnerabilities by building exploit chains (A→B→C)
Chain Findings
**Rule reference (R12):** the NEVER SUBMIT list and `chain_with[]` requirement live in `.claude/rules/hunting.md` Rule 17. The save-finding gate that enforces them is Rule 10b. R25 (chain_with validator) rejects chains anchored to dead findings. This skill describes the THINKING; the rule numbers are authoritative.
Take low/medium findi
Alternatives in Security
- Security Best Practices — Review code for language-specific security vulnerabilities 14.6k ★
- Deepsec — Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents 7.8k ★
- Claude Code Security Review — An AI-powered security review GitHub Action using Claude to analyze code changes for security vulnerabilities 3.9k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
/chain
Build an A→B→C exploit chain for higher severity and payout.
Chain
Build an exploit chain — given bug A, finds B and C to combine for higher severity and payout. Knows common ch
Exploit Chain
Chain multiple findings into a single multi-step exploit. Produces a Foundry test that proves the chain works.
Audit Multi Chain
Diff the on-chain configuration of one contract deployed across multiple chains — owner, oracle, fees, timeloc
Audit Codebase
Cold-start, time-boxed, multi-domain audit sweep — surfaces ranked findings with reasoning chains across secur
Cybersec 10000
40-agent, ~10,163-dimension security analysis swarm (static + live ops) with a scored 46-chain exploit planner
Related Agents
Exploit Chainer
Delegates to this agent when the user wants to automatically chain isolated vulnerabilities into multi-step at
Attack Ideator
Phase 10 Review Chamber creative attack hypothesis generator that thinks like a hacker, chains low-severity is
Finding Chain Synthesizer
Chains confirmed audit findings into multi-step, cross-domain exploit candidates and searches for a unique eme