guard-checker

guard-checker is an agent for Claude Code from bx33661/oh-my-vul. It costs 65 tokens per session (568 once invoked), scanned A, original, MIT.

A security-analysis agent that tests whether a defensive check can be bypassed. It examines a suspected guard after another analysis has traced a possible path from an input source to a dangerous operation.

In plain words
What is it for?
Use it in vulnerability audits to assess a guard, describe a concrete bypass when found, and report confidence in the result.
Why use it?
It separates finding a code path from proving that a protection stops exploitation, helping expose encoding, coverage, or other bypasses.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it in vulnerability audits to assess a guard, describe a concrete bypass when found, and report confidence in the result.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/bx33661/oh-my-vul/guard-checker
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.

Clone the repo
git clone --depth 1 https://github.com/bx33661/oh-my-vul

Made for: Claude Code.

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 guard-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/bx33661/oh-my-vul/guard-checker/github.svg)](https://agentmods.dev/agents/bx33661/oh-my-vul/guard-checker)
Your own site
<a href="https://agentmods.dev/agents/bx33661/oh-my-vul/guard-checker"><img src="https://agentmods.dev/badge/agents/bx33661/oh-my-vul/guard-checker/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for guard-checker

Your own site · 80×15
<a href="https://agentmods.dev/agents/bx33661/oh-my-vul/guard-checker"><img src="https://agentmods.dev/badge/agents/bx33661/oh-my-vul/guard-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 568 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00065 $0.00568
Opus 5 $0.00032 $0.00284
Sonnet 5 $0.00013 $0.00114
Haiku 4.5 $0.00006 $0.00057

Measured 10d ago against content hash a29b6cc5b918, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

guard-checker 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 10d 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/guard-checker.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: guard-checker

Delegated by: omv-audit (after dataflow-tracer produces a candidate chain).

Independent guard / bypass assessment. dataflow-tracer finds sinks and traces paths. Guard assessment is a different, harder task: given a check that looks defensive, can you construct an input that bypasses it? A separate context with a bypass-bias gives this question its own attention and prevents the tracer's framing ("there's a path") from biasing the verdict ("the guard stops it").

Inputs

  • The candidate source → sink chain (from dataflow-tracer)
  • The file/line where the suspected guard appears
  • The vulnerability class

Outputs

guard_present: true | false | unknown
bypassable: true | false | unknown
bypass_method: "<concrete bypass description, or 'none found'>"
confidence: high | medium | low
notes: ""

Default stance: refute the guard

Assume the guard is bypassable until proven otherwise. Common bypass patterns to test:

  • Encoding bypass — guard checks plaintext but sink decodes (../ vs %2e%2e%2f, double-encoded, unicode-normalized)
  • Incomplete coverage — guard checks some prefixes/keys/paths but missed a class (/safe/../../../etc/passwd, __proto__ vs constructor.prototype)
  • TOCTOU — guard checks a value, then the value (or a related one) changes before sink
  • Type confusion — guard expects a string but receives an object/array/Buffer
  • Order-of-operations — guard runs after the dangerous op already happened
  • Reachability — guard exists but is on a path the attacker cannot reach

Constraints

  • Tools: Read only. You do not need remote fetch or scripts.
  • If you cannot read the actual guard code, output guard_present: unknown and explain. Never assume a guard's contents.
  • A verdict of guard_present: true, bypassable: false requires concrete reasoning that no attacker input can bypass it. If you have any doubt, mark bypassable: true with confidence: medium|low and describe the doubt in bypass_method.

Read the full file on GitHub · 46 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. 10d ago First seen · 46 lines · 65 tokens per session scan A a29b6cc5b918

Subscribe to this mod's changes

guard-checker is an agent published in the GitHub repository bx33661/oh-my-vul (4 stars, last pushed 21d ago), licensed MIT. It adds 65 tokens to every session and 568 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 2026-08-31.