DQIII8: Skill for Claude Code

.claude/skills/red-team/SKILL.md

red-team is a skill for Claude Code from senda-labs/DQIII8. It costs 61 tokens per session (2,695 once invoked), scanned A, original, MIT.

An adversarial security test that tries to break a codebase using techniques associated with real attackers, including checks based on the OWASP Top 10 security risks.

In plain words
What is it for?
Use it to test exposed services and endpoints, probe authentication, and produce an exploit report for the current project or a selected component.
Why use it?
It looks for weaknesses that ordinary static checks may miss, including problems in deployment, dependencies, authentication, and agent-related patterns.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter; reads .claude/ paths.

This is senda-labs/DQIII8's own configuration. It tells Claude Code how to work on DQIII8 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything DQIII8 configures →

Part of the dqiii8 plugin — 22 skills, 14 commands, 17 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to senda-labs/DQIII8. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/senda-labs/DQIII8/main/.claude/skills/red-team/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/senda-labs/DQIII8

Made for: Claude Code.

Or install dqiii8, the plugin that ships this one along with the rest of its 22 skills, 14 commands, 17 agents.

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 red-team

README.md
[![agentmods](https://agentmods.dev/badge/skills/senda-labs/dqiii8/red-team/github.svg)](https://agentmods.dev/skills/senda-labs/dqiii8/red-team)
Your own site
<a href="https://agentmods.dev/skills/senda-labs/dqiii8/red-team"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/red-team/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 red-team

Your own site · 80×15
<a href="https://agentmods.dev/skills/senda-labs/dqiii8/red-team"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/red-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,695 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 118
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 130
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 145
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium Tool Misuse · line 54
    Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.
    Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
How audits are shown
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 $0.00061 $0.02695
Opus 5 $0.00030 $0.01347
Sonnet 5 $0.00012 $0.00539
Haiku 4.5 $0.00006 $0.00269

Measured 12d ago against content hash 5f171be661fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

red-team 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

result=$(curl -s --connect-timeout 2 -o /dev/null -w "%{http_code}" http://localhost:$port 2>/dev/null)
.claude/skills/red-team/SKILL.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/red-team — Adversarial Security Testing

Attack the codebase like a real hacker. Find vulnerabilities that static scanners miss. Think like an attacker, not a checker.

Usage

/red-team                          # Full attack on current project
/red-team $ARGUMENTS               # Attack specific path or component

Philosophy

  • You are NOT a scanner. You are an attacker.
  • Think: "How would I break this?" not "Does this follow best practices?"
  • Chain vulnerabilities: a LOW finding + another LOW = potential CRITICAL
  • Test the DEPLOYMENT, not just the code (env vars, permissions, exposed ports)
  • Vibe-coded patterns are predictable — exploit that predictability

Attack Phases

Phase 0: External Attack Surface

Start here — simulate an external attacker with no inside knowledge:

  1. Port scan — discover exposed services:
    for port in 22 80 443 3000 5000 8000 8080 8443 9000; do
      result=$(curl -s --connect-timeout 2 -o /dev/null -w "%{http_code}" http://localhost:$port 2>/dev/null)
      [ "$result" != "000" ] && echo "  port $port → HTTP $result"
    done
    ss -tlnp | grep LISTEN
    
  2. Auth endpoints — probe without credentials:
    for path in / /api /api/health /api/admin /admin /metrics /debug; do
      code=$(curl -s --connect-timeout 2 -o /dev/null -w "%{http_code}" http://localhost:8000$path 2>/dev/null)
      echo "  $path → $code"
    done
    
  3. CORS test — check for misconfigured cross-origin policy:
    curl -s -H "Origin: https://evil.com" -I http://localhost:8000/ 2>/dev/null | grep -i "access-control"
    
  4. fail2ban — verify brute-force protection:
    fail2ban-client status 2>/dev/null || echo "fail2ban not running — SSH brute-force unprotected"
    fail2ban-client status sshd 2>/dev/null | grep -E "banned|failed"
    
  5. SSL/TLS — check cipher weaknesses if HTTPS is exposed.

Phase 1: Reconnaissance

Map the internal attack surface:

# Find all entry points (web routes, API endpoints, CLI args)
grep -rn "@app\.\|@router\.\|argparse\|sys.argv" --include="*.py" .
# Find all external connections (DB, API, network)
grep -rn "connect\|requests\.\|urllib\|subprocess\|exec\|eval" --include="*.py" .
# Find authentication mechanisms
grep -rn "auth\|token\|session\|cookie\|password\|jwt\|oauth" --include="*.py" .
# Find file operations (path traversal candidates)
grep -rn "open(\|Path(\|os.path\|shutil" --include="*.py" .
# Map MCP servers and their permissions
cat ~/.claude.json 2>/dev/null | python3 -c "import json,sys; [print(f'MCP: {k}') for k in json.load(sys.stdin).get('mcpServers',{}).keys()]"

Read the full file on GitHub · 249 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. 12d ago First seen · 249 lines · 61 tokens per session scan A 5f171be661fb

Subscribe to this mod's changes

red-team is a skill published in the GitHub repository senda-labs/DQIII8 (11 stars, last pushed 23d ago), licensed MIT. It adds 61 tokens to every session and 2,695 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.