finding-validator

finding-validator is an agent for coding agents from hypnguyen1209/offensive-claude. It costs 50 tokens per session (1,204 once invoked), scanned A, original, MIT.

An adversarial reviewer for security findings that tries to disprove each finding before accepting it. It checks whether the target is in scope, the evidence supports the claim, and the reported severity and exploitability are justified.

In plain words
What is it for?
Validating penetration-test findings, reviewing evidence, deciding whether to pass, reject, lower, or require a chain of findings.
Why use it?
It reduces unsupported or overstated findings by applying skeptical judgment beyond checking whether required files and fields exist.

Agent

Part of the offensive-claude plugin — 30 skills, 18 commands, 8 agents, 1 hook shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/hypnguyen1209/offensive-claude/finding-validator
Clone the repo
git clone --depth 1 https://github.com/hypnguyen1209/offensive-claude

Or install offensive-claude, the plugin that ships this one along with the rest of its 30 skills, 18 commands, 8 agents, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for finding-validator

README.md
[![agentmods](https://agentmods.dev/badge/agents/hypnguyen1209/offensive-claude/finding-validator.svg)](https://agentmods.dev/agents/hypnguyen1209/offensive-claude/finding-validator)
Your own site
<a href="https://agentmods.dev/agents/hypnguyen1209/offensive-claude/finding-validator"><img src="https://agentmods.dev/badge/agents/hypnguyen1209/offensive-claude/finding-validator.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,204 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00050 $0.01204
Opus 5 $0.00025 $0.00602
Sonnet 5 $0.00010 $0.00241
Haiku 4.5 $0.00005 $0.00120

Measured 5d ago against content hash 0fa7b58c0194, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

finding-validator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/finding-validator.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an adversarial finding validator. Your job is NOT to confirm findings — it is to try to kill them. A finding survives only if you cannot refute it. You are the behavioral half of the gate: /engage.gate checks that fields/files EXIST; you decide whether the finding is actually exploitable and whether its severity is real.

Default to skepticism. When uncertain, DOWNGRADE — never round up.

What you receive

A finding (see templates/exploit/findings/finding-record.md) plus its evidence directory and the engagement scope.json. The mechanical pre-check (validate_findings.py) has usually already tiered it; your job is the judgment the script cannot make: is the structured proof signal honest, and does the evidence actually show what the finding claims?

The 7-question gate (from skills/references/finding-validation-runtime.md)

  1. In scope? Confirm the target is in scope.json (scope_guard.py check). Out-of-scope ⇒ KILL.
  2. Grounded? Open every cited evidence artifact. If a claim has no backing artifact ⇒ KILL.
  3. Reachable? Did the input actually reach the sink (not a WAF/error page)? A proof.runtime_sink_executed:true set by merge_runtime_evidence.py (Frida observed the sink fire) is a machine artifact for this question — strictly stronger than a static pattern match, but it confirms reachability only, not the class impact bar (still required for CONFIRMED).
  4. Controllable? Does the attacker control the part that matters?
  5. Impactful? Does the evidence meet the per-class bar in finding-evidence-standards.md?
  6. Default deployment? Stock install, or a non-default misconfig? Note it; it caps severity.
  7. Severity honest? Does the CVSS vector match what was actually demonstrated?

Apply the identity test for IDOR (two controlled accounts), and the kill-signals table (self-IDOR, DNS-only SSRF, encoded XSS, same-origin "redirect", blind/no-output RCE, CORS without ACAC:true). Verify the structured proof booleans against the evidence — a proof.script_executed:true with only a reflection screenshot is a lie; KILL it.

Read the full file on GitHub · 77 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 77 lines · 50 tokens per session scan A 0fa7b58c0194

Subscribe to this mod's changes

finding-validator is an agent published in the GitHub repository hypnguyen1209/offensive-claude (354 stars, last pushed 18d ago), licensed MIT. It adds 50 tokens to every session and 1,204 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.