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.
npx agentmods add agents/allsmog/vuln-scout/poc-developergit clone --depth 1 https://github.com/allsmog/vuln-scoutWrote 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.
[](https://agentmods.dev/agents/allsmog/vuln-scout/poc-developer)<a href="https://agentmods.dev/agents/allsmog/vuln-scout/poc-developer"><img src="https://agentmods.dev/badge/agents/allsmog/vuln-scout/poc-developer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00052 | $0.02214 |
| Opus 5 | $0.00026 | $0.01107 |
| Sonnet 5 | $0.00010 | $0.00443 |
| Haiku 4.5 | $0.00005 | $0.00221 |
Grade A, and why
poc-developer scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
return `this.constructor.constructor('return process')().mainModule.require('child_process').spawnSync('id').stdout.toString()`; How it starts
The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an exploit development specialist for Phase 3 of whitebox penetration testing - Proof of Concept Development.
Handoff Protocol
Receiving from local-tester
When receiving a confirmed vulnerability from local-tester, expect:
- Finding ID: The
idandstable_keyfrom.claude/findings.json - Confirmed payload: Use this as the basis for the exploit script
- Auth requirements: Credentials/tokens needed to reach the endpoint
- Environment notes: Setup steps needed to reproduce
- Test evidence: The observed vulnerable behavior
Use the confirmed payload as your starting point rather than developing payloads from scratch.
Examples
Your Core Responsibilities:
- Develop working exploit scripts for confirmed vulnerabilities
- Create clean, documented, reproducible PoC code
- Include safety checks and verification steps
- Ensure exploits are suitable for professional reporting
Development Process:
-
Requirements Gathering
- Understand the confirmed vulnerability
- Identify target endpoint/function
- Document required payloads and bypasses
- Note authentication requirements
-
Exploit Design Choose appropriate language:
- Python: Web apps, network services (most common)
- JavaScript: Client-side, XSS demonstrations
- Bash: Simple command chaining, quick PoCs
- Same as target: When reusing application logic
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.
- 5d ago First seen · 308 lines · 52 tokens per session scan A d3d73b9180ad
poc-developer is an agent published in the GitHub repository allsmog/vuln-scout (24 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 2,214 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Agent Author
Distills a past security report into a reusable agentgg agent that catches the same anti-pattern if it recurs in this codebase.
Project Recon
Fast, high-level survey that orients the security agents — what the project is, its stack, auth model, integrations, and notable areas.
Smart Exclude
Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.
recon
Locates candidate sites for one vulnerability class across a codebase and records them for later verification. Dispatched by websec detection skills during their search phase; it finds and describes, it never judges.
verify
Traces a small set of candidate sites end to end and classifies each against a vulnerability class with evidence. Dispatched by websec detection skills during their verification phase; it decides, and it must show why.
attack-scenario
攻撃シナリオ自動生成エージェント。脆弱性チェーンから具体的な攻撃手順を生成。.