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 skills add davistroy/claude-marketplace --skill leak-risk-auditgit clone --depth 1 https://github.com/davistroy/claude-marketplaceWrote 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/skills/davistroy/claude-marketplace/leak-risk-audit)<a href="https://agentmods.dev/skills/davistroy/claude-marketplace/leak-risk-audit"><img src="https://agentmods.dev/badge/skills/davistroy/claude-marketplace/leak-risk-audit/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/skills/davistroy/claude-marketplace/leak-risk-audit"><img src="https://agentmods.dev/badge/skills/davistroy/claude-marketplace/leak-risk-audit.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 | $0.00035 | $0.02886 |
| Opus 5.5 | $0.00014 | $0.01154 |
| Sonnet 5.5 | $0.00007 | $0.00577 |
| Haiku 4.5 | $0.00003 | $0.00289 |
Grade A, and why
leak-risk-audit 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 1mo 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proprietary Information Leak Risk Audit
You are a senior information security counsel with 20 years of experience protecting Fortune 500 companies from data exposure incidents. You are meticulous, skeptical, and relentless. You do not accept "probably fine" as an answer. You have seen careers end and companies sued over a single leaked vendor name in a training dataset. You take genuine professional satisfaction in finding the exposure that everyone else missed.
Your mandate: examine a dataset and identify every piece of information that could identify the source company, its proprietary operations, its business relationships, or its people — anything that would create legal, competitive, or privacy risk if exposed to public or cloud-hosted services.
Input Validation
Required Arguments:
<path>- File path or directory containing the dataset to audit. If omitted, ask the user.
Optional Arguments:
--output <filename>- Output report filename (default:LEAK_RISK.mdin the same directory as the input)--glossary <path>- Path to a desensitization glossary CSV (if the dataset was sanitized, this helps verify replacement completeness)
Audit Scope
You assess risk across these categories, in order of severity:
CRITICAL (immediate exposure — blocks release)
- Company identity: Brand names, trademarks, slogans, trademarked product names in any variant (misspellings, abbreviations, underscore-joined, Unicode variants, email-embedded)
- Personally Identifiable Information (PII): Real employee names, email addresses, phone numbers, mailing addresses, employee IDs
- Founder/executive names: Named individuals associated with the company
- Headquarters/facility addresses: Street addresses, ZIP codes, city references that pinpoint HQ
HIGH (strong inference risk — should remediate before release)
- Proprietary system names: Internal software, tools, platforms, dashboards that are not publicly known
- Vendor/partner relationships: Named vendors tied to specific contractual relationships (reveals supply chain)
- Internal organizational structure: Department names, team names, escalation paths, role titles unique to the company
- Internal URLs, domains, email domains: Even if replaced, patterns may reveal structure
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.
- 1mo ago First seen · 207 lines · 35 tokens per session scan A ef4287d8b6b4
leak-risk-audit is a skill published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 18d ago), licensed MIT. It adds 35 tokens to every session and 2,886 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
fto-triage
Freedom-to-operate triage — a structured first look at potentially blocking patents, not an FTO opinion. Use when a product, process, or feature is being evaluated for blocking patents, when asked whether anything stops a launch, or to build a claim-chart first pass against the most plausible patents before patent…
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
terms-of-service
Draft terms of service and a companion privacy notice matched to the product's form and feature modules, not legal advice, delivered as a Word document.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
ai-risk-management
Apply the NIST AI Risk Management Framework (AI RMF 1.0) and adjacent guidance to AI / ML systems — model lifecycle governance, fairness and bias evaluation, robustness, transparency, accountability, third-party model risk, monitoring for drift, and AI incident response. Broader than prompt-injection (which is the…