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 kensaurus/cursor-kenji --skill audit-securitygit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWrote 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/kensaurus/cursor-kenji/audit-security)<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/audit-security"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/audit-security/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/kensaurus/cursor-kenji/audit-security"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/audit-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
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 Output Handling · line 215 Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.Fix: Validate and sanitize all model output before using it in downstream contexts. Use parameterized queries for SQL, shell quoting for commands, and HTML encoding for web output.
- high Output Handling · line 222 Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.Fix: Validate and sanitize all model output before using it in downstream contexts. Use parameterized queries for SQL, shell quoting for commands, and HTML encoding for web output.
- high Privilege Escalation · line 270 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 272 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.
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 | $0.00065 | $0.02509 |
| Opus 5.5 | $0.00026 | $0.01004 |
| Sonnet 5.5 | $0.00013 | $0.00502 |
| Haiku 4.5 | $0.00006 | $0.00251 |
Grade A, and why
audit-security 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Audit Skill
Degree of freedom: MIXED — Steps 0–4 judgment [HIGH freedom];
dependency and secret scans [LOW freedom — run exactly]. Never write
exploit PoCs.
Audit-and-fix exception. May fix inline. Plan-only burndown →
plan-security-audit. When fixing inline: patch the evidenced sink only, in place; unrelated weaknesses you notice go in the report as findings, not fixes. Add a test only where the repo already keeps security tests or the task asks. Auth behavior, RLS, secrets rotation, payments, and migrations stay STOP-and-confirm.
OWASP static review (injection, headers, deps). Session / route×gate /
getSession() → audit-auth-flows. Next.js 16: grep middleware.ts and
proxy.ts — a route gate can live in either file, and the proxy layer has its own bypass class.
How to reason
- Observe — quote the sink or missing check (
file:line) - Interpret — can untrusted input reach a query, HTML, or object-id?
- Classify — injection / IDOR / secret / header / dep-CVE / hand-off
- Severity — exploitable data access or hardcoded secret = Critical
Worked example
Observe:
GET /documents/:idloads by id only (api/docs/route.ts:18). Interpret: any caller who can hit the route reads another user's doc. Classify: IDOR. Severity: Critical. Finding: IDOR |/documents/:id| adduserIdpredicate. Matcher /getSession()on that route →audit-auth-flows, not this checklist.
Step 0: Understand the Project [HIGH freedom]
Before auditing, discover the tech stack and attack surface:
- Read
package.json/requirements.txt/go.modto identify:
- Auth library (next-auth, passport, supabase-auth, django-auth, etc.)
- Database ORM (Prisma, Sequelize, SQLAlchemy, etc.)
- HTTP framework (Express, Fastify, Django, Flask, etc.)
- Any security-specific packages (helmet, cors, csurf, rate-limit, etc.)
- Identify the auth pattern:
- Session-based vs JWT vs OAuth
- Where tokens are stored (cookies, localStorage, headers)
- How permissions/roles are enforced
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 Changed · -49 lines · -9 tokens per session 5519d9bc424f
- 1mo ago First seen · 339 lines · 74 tokens per session scan A eaeeff487d0a
audit-security is a skill published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 27d ago), licensed MIT. It adds 65 tokens to every session and 2,509 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
python-dev
Python backend conventions for this project. Use when implementing or modifying API endpoints, database models/migrations, services, schemas, or backend tests.
developing-genkit-dart
Use when building AI agents in Dart, implementing Genkit flows or tools, integrating LLMs into Dart or Flutter applications, or using Genkit Dart plugins.
create-handler
Create a new API handler following the handler pattern. Use when the user asks to create an endpoint, handler, or route.
generate-api-docs
Generate API documentation from code.
api-docs
Workflow for creating comprehensive API documentation. Use when the user needs to document API endpoints.
opensearch
Workflow for OpenSearch (or Elasticsearch) usage: indexing, search, mappings, and tuning. Use when the user asks about OpenSearch/Elasticsearch.