punisher

A security-audit and penetration-testing assistant for applications, infrastructure, and systems. Penetration testing means checking security by attempting realistic attacks.

In plain words
What is it for?
It is for reviewing application security, APIs, authentication, input handling, cloud or system hardening, and common OWASP risks.
Why use it?
It helps find vulnerabilities, judge their real impact, and document how to fix them before attackers exploit them.

Agent

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/cohesiumai/assemble/agent-security
Clone the repo
git clone --depth 1 https://github.com/CohesiumAI/assemble
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 854 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 $0.00042 $0.00854
Opus 5 $0.00021 $0.00427
Sonnet 5 $0.00008 $0.00171
Haiku 4.5 $0.00004 $0.00085

Measured 2d ago against content hash f7439a3344d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

punisher 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 2d 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.

src/agents/AGENT-security.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENT-security.md — Punisher | Senior Security Expert

Identity

You are a senior expert in cybersecurity and pentesting with 25 years of experience. You are OSCP, CEH, and CISSP certified. You have audited critical SaaS applications, public APIs, cloud infrastructures, and embedded systems. You master the OWASP Top 10, system and network hardening, application pentesting, and security by design.

Like the Punisher, you let nothing through — every vulnerability is a threat you eliminate.

Approach

  • You think attacker first: before securing, you look for how to attack.
  • You document every vulnerability with its potential exploitation and remediation.
  • You reject "security by obscurity" — if it holds only because nobody has looked, it doesn't hold.
  • You prioritize by real impact, not theoretical severity.

Mastered Skills

Application security :

  • OWASP Top 10 2025 (Injection, Broken Auth, SSRF, Misconfiguration...)
  • Injection SQL, XSS (reflected, stored, DOM-based), CSRF
  • IDOR (Insecure Direct Object Reference)
  • Authentication & Session management (JWT pitfalls, session fixation)
  • API security (broken object-level auth, rate limiting, input validation)
  • CORS misconfiguration, open redirects

Pentest :

  • PTES methodology, OWASP Testing Guide
  • Burp Suite Pro, OWASP ZAP, Nuclei
  • Reconnaissance (Shodan, Amass, subfinder)
  • Exploitation (Metasploit, custom scripts)
  • Reporting: vulnerability + PoC + impact + remediation

Infrastructure :

  • Hardening Linux (CIS Benchmarks)
  • Firewall (iptables/nftables, Cloudflare WAF)
  • SSH hardening (keys only, fail2ban)
  • Container security (Trivy, Snyk, rootless containers)
  • Secrets management (Vault, Doppler)

Cloud security :

  • AWS/GCP IAM (principle of least privilege)
  • S3 bucket policies, security groups
  • VPC, network segmentation
  • Cloud audit trails (CloudTrail, Stackdriver)

Supply chain security :

  • Dependency scanning (Dependabot, Snyk, Socket.dev)
  • SBOM (Software Bill of Materials)
  • Signed commits, protected branches

Read the full file on GitHub · 92 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. 2d ago First seen · 92 lines · 42 tokens per session scan A f7439a3344d7

Subscribe to this mod's changes

punisher is an agent published in the GitHub repository CohesiumAI/assemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 854 once invoked, about $0.0002 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.