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 h4vzz/awesome-ai-agent-skills --skill security-auditgit clone --depth 1 https://github.com/h4vzz/awesome-ai-agent-skillsWrote 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/h4vzz/awesome-ai-agent-skills/security-audit)<a href="https://agentmods.dev/skills/h4vzz/awesome-ai-agent-skills/security-audit"><img src="https://agentmods.dev/badge/skills/h4vzz/awesome-ai-agent-skills/security-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/h4vzz/awesome-ai-agent-skills/security-audit"><img src="https://agentmods.dev/badge/skills/h4vzz/awesome-ai-agent-skills/security-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 | $0.00029 | $0.01905 |
| Opus 5 | $0.00015 | $0.00953 |
| Sonnet 5 | $0.00006 | $0.00381 |
| Haiku 4.5 | $0.00003 | $0.00191 |
Grade A, and why
security-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 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.
This is a copy
91% identical to security-audit — 9 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Audit
This skill enables the agent to conduct a thorough security audit across web applications, APIs, cloud infrastructure, and backend services. The agent systematically examines authentication mechanisms, authorization controls, input validation, encryption practices, logging configurations, and deployment settings. Findings are mapped to industry frameworks such as the OWASP Top 10, CWE identifiers, and compliance standards including SOC 2 and PCI-DSS.
Workflow
-
Gather System Information — Collect details about the target environment including the technology stack, architecture diagrams, network topology, deployment model, and third-party integrations. Review configuration files, environment variables, and infrastructure-as-code templates to build a complete picture of the attack surface.
-
Define Audit Scope and Compliance Targets — Establish the boundaries of the audit by identifying which components, environments, and data flows are in scope. Map audit objectives to relevant compliance frameworks such as SOC 2 Type II, PCI-DSS, HIPAA, or internal security policies. Create a checklist derived from the OWASP Top 10 and CWE/SANS Top 25 to ensure systematic coverage.
-
Perform Automated Vulnerability Scanning — Run automated scanners against the target to identify known vulnerabilities. Use tools like OWASP ZAP for web applications, Trivy or Grype for container images, and ScoutSuite or Prowler for cloud infrastructure. Aggregate raw findings for manual review.
-
Conduct Manual Security Review — Manually inspect authentication flows, session management, role-based access controls, input sanitization routines, cryptographic implementations, error handling, and logging practices. Examine source code for hardcoded secrets, insecure deserialization, and business logic flaws that automated tools frequently miss.
-
Analyze and Classify Findings — Assess each finding for severity (Critical, High, Medium, Low, Informational) using CVSS scoring. Assign CWE identifiers and map findings to the relevant OWASP Top 10 category. Evaluate exploitability, blast radius, and business impact to produce a prioritized risk ranking.
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 · 135 lines · 29 tokens per session scan A 269393e89dc8
security-audit is a skill published in the GitHub repository h4vzz/awesome-ai-agent-skills (34 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 1,905 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to security-audit, differing in 9 lines, and is treated as a copy.
Other skills, from other repositories
general-counsel-reviewer
Reviews a proposal, business case, deck or plan in character as a General Counsel archetype, then saves a structured review document with a verdict, findings that cite the artifact, legal risks and five interrogation questions. Use when the user asks for a legal review, a general counsel pressure-test of a document…
procurement-reviewer
Reviews a proposal, business case, deck or vendor contract in character as a Head of Procurement archetype, then saves a structured review document with a verdict, findings that cite the artifact, commercial risks and five interrogation questions. Use when the user asks for a procurement review, a commercial or…
contract-review-pack
Abstracts one contract into a key-terms table, compares each term against the user's own playbook of standard positions, and produces a DRAFT contract review pack with a deviations and issues list, open questions and a reviewer checklist. Flags governing law and never gives legal advice, interpretation, or…
dpia-draft-pack
Reads a project or processing description and produces a DRAFT DPIA pack — processing description, necessity and proportionality questions, a risk table with rating cells left blank, mitigations to consider, and open questions. Never rates risk, determines the lawful basis, or judges adequacy; the DPO assesses and…
controls-gap-pack
Reads a requirement, regulation, or policy and the organisation's control descriptions, then produces a DRAFT controls-and-gap pack — the requirement broken into obligations, mapped controls, apparent coverage, gaps, and actions to assess. Never concludes compliance or that a control is effective; control owners and…
export-review-pack
Reads a transaction or order description and produces a DRAFT export review pack — a parties-to-screen list and checklist, a classification worksheet, a red-flag review, and licence-determination questions — to prepare an export-control review. Never classifies, screens, clears, or decides a licence; trade compliance…