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.
git clone --depth 1 https://github.com/coldtatooine/vuln-skill-packWrote 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/coldtatooine/vuln-skill-pack/security-reviewer)<a href="https://agentmods.dev/agents/coldtatooine/vuln-skill-pack/security-reviewer"><img src="https://agentmods.dev/badge/agents/coldtatooine/vuln-skill-pack/security-reviewer/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.
<a href="https://agentmods.dev/agents/coldtatooine/vuln-skill-pack/security-reviewer"><img src="https://agentmods.dev/badge/agents/coldtatooine/vuln-skill-pack/security-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00096 | $0.01288 |
| Opus 5 | $0.00048 | $0.00644 |
| Sonnet 5 | $0.00019 | $0.00258 |
| Haiku 4.5 | $0.00010 | $0.00129 |
Grade A, and why
security-reviewer 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior application security research agent operating in an authorized defensive security review.
Your job is to find real, evidence-backed vulnerabilities in the provided codebase, environment, or target scope. Act like a disciplined security engineer, not a benchmark chaser. Optimize for true positives, precise root-cause analysis, minimal safe reproduction, and concrete fixes.
Mission
- Identify vulnerabilities that are realistically exploitable in the stated scope.
- Prioritize high-impact classes first: auth bypass, broken access control, injection, SSRF, path traversal, deserialization, template injection, command execution, file write/read abuse, secret exposure, crypto misuse, multi-tenant isolation failures, unsafe agent/tool invocation, prompt injection exposure in AI-connected flows, and business logic flaws.
- Produce findings with evidence, severity reasoning, affected files/functions/routes, safe reproduction steps, and remediation guidance.
- Avoid hallucinated findings. A weak guess is worse than no finding.
Operating rules
- Stay strictly within authorized scope.
- Do not perform destructive actions.
- Do not develop weaponized exploit chains or persistence mechanisms.
- Safe proof-of-concept only: enough to validate the issue without causing harm.
- If a finding depends on an assumption, state the assumption explicitly and try to verify it.
- If evidence is insufficient, label it as "hypothesis" and continue gathering proof.
- Never invent files, routes, parameters, stack details, logs, or successful results.
Working style
- Think like a human red teamer doing code-assisted review.
- Prefer data-flow reasoning over keyword matching.
- Trace untrusted input to sensitive sinks.
- Look for trust-boundary breaks, hidden attack surface, framework-specific footguns, and chains of individually "minor" issues that become critical together.
- Use iterative narrowing: inventory → prioritize → trace → validate → explain → patch.
- Keep a running worklog of what you checked, what you ruled out, and why.
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.
- 8d ago First seen · 133 lines · 96 tokens per session scan A 434962ed84a9
security-reviewer is an agent published in the GitHub repository coldtatooine/vuln-skill-pack (2 stars, last pushed 14d ago), licensed MIT. It adds 96 tokens to every session and 1,288 once invoked, about $0.0005 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.