Verifier Defenses — Security agent for Claude Code
Evaluates whether existing sanitizers, validation schemas, or security barriers neutralize the candidate.
How to install Verifier Defenses
Installs to ~/.claude/agents/arcobaleno64-agy-security-audit-verifier-defenses.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/arcobaleno64/agy-security-audit/HEAD/agents/verifier-defenses.md -o ~/.claude/agents/arcobaleno64-agy-security-audit-verifier-defenses.md Restart Claude Code, or start a new session, for it to be picked up.
What Verifier Defenses does
name: verifier-defenses description: Evaluates whether existing sanitizers, validation schemas, or security barriers neutralize the candidate. mainAgent: false subagent: true commandExecutionPolicy: off tools:
- view_file
- list_dir
- grep_search
- find_by_name
Role: Verifier Panelist — DEFENSES Lens
You are an independent verifier evaluating candidate vulnerabilities strictly through the **DEFENSES** lens.
Evaluation Mandate
You must answer: **Do existing sanitizers, in
Alternatives in Security
- Retool Endpoint Audit — Checks a migration slice against the main app's API surface — whether a local implementation duplicates an exi 7.2k ★
- Audit Verifier — Adversarially verifies one candidate finding from /bug-audit — tries to REFUTE it by reading the code and, whe 335 ★
- Security Verifier — You write and execute PoC tests to PROVE bugs exist 215 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Cto Security Posture
CTO-grade security posture review. Evaluates real security vs security theater. Tests whether controls actuall
Vuln Verifier
Adjudicates a single candidate security finding produced by the vuln-analyst hunter. Independently re-reads th
Cs Scan Verifier
description: Restricted read-only verifier dispatched by the Claude Security scan workflow to vote on one cand
Exploit Verifier Prosecutor
Phase 4 of the mobile-security-skill pipeline (half of the adversarial exploitation panel). Builds the stronge
Pentest Validator
Optional, disabled-by-default Dynamic Security Validation agent. Interacts with a running, explicitly authoriz
Exploit Validator
Adversarial validation specialist. Receives candidate findings it did NOT discover and tries to refute each on
Related Skills
Reviewer Verify
You are the adversarial verifier for the candidate pull-request findings raised against one file. Your only jo
Prompt Injection Benchmark
A reproducible prompt-injection benchmark that measures which defenses actually work: each payload is replayed
Ralph Run Diagnostics
Evaluates whether the RALPH loop followed policy: correct task selection, verification level selection, requir