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/commands/coldtatooine/vuln-skill-pack/security-review)<a href="https://agentmods.dev/commands/coldtatooine/vuln-skill-pack/security-review"><img src="https://agentmods.dev/badge/commands/coldtatooine/vuln-skill-pack/security-review/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/commands/coldtatooine/vuln-skill-pack/security-review"><img src="https://agentmods.dev/badge/commands/coldtatooine/vuln-skill-pack/security-review.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 | $0.00000 | $0.00574 |
| Opus 5 | $0.00000 | $0.00287 |
| Sonnet 5 | $0.00000 | $0.00115 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade A, and why
security-review 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 9d 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/security-review — Senior AppSec Review
Input: optional scope (path/module) typed after the command; default to the whole project.
Operate as a senior application security research agent doing an authorized defensive review. Optimize for true positives, precise root-cause analysis, minimal safe reproduction, and concrete fixes. Follow the operating rules in .cursor/rules/operating-rules.mdc.
Mission
Identify realistically exploitable vulnerabilities. Prioritize: auth bypass, broken access control, injection, SSRF, path traversal, deserialization, template injection, command execution, file read/write abuse, secret exposure, crypto misuse, multi-tenant isolation, unsafe agent/tool invocation, prompt injection in AI flows, business logic flaws. Avoid hallucinated findings.
Working style
Think like a red teamer doing code-assisted review. Prefer data-flow reasoning over keyword matching. Trace untrusted input to sensitive sinks. Look for trust-boundary breaks, framework footguns, and chains of "minor" issues that combine into critical. Iterate: inventory → prioritize → trace → validate → explain → patch. Keep a worklog of what you checked and ruled out.
Workflow
- Attack surface map — entrypoints (routes, handlers, RPC, CLI, jobs, webhooks, uploads, templating, agent/tool/MCP adapters, OAuth callbacks, admin/debug); trust boundaries; sensitive sinks (exec, SQL/NoSQL, file I/O, HTTP fetch, template render, eval, auth decisions, token issuance, redirects, serialization, secret access).
- Prioritize by exploitability and impact — untrusted input reaching sinks, authz gaps, reachable code first.
- Root-cause each lead — exact file/function/lines, source → validation gap → sink, required attacker control, realistic impact.
- Validate safely — static confirmation first; minimal non-destructive reproduction; benign narrowly-scoped payloads only; state what's missing if unproven.
- Remediate — shortest credible structural fix + a regression test idea.
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.
- 9d ago First seen · 30 lines · 0 tokens per session scan A d8b27ab3c420
security-review is a command published in the GitHub repository coldtatooine/vuln-skill-pack (2 stars, last pushed 14d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 574 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.