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 cwinvestments/memstack --skill owasp-top10git clone --depth 1 https://github.com/cwinvestments/memstackWrote 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/cwinvestments/memstack/owasp-top10)<a href="https://agentmods.dev/skills/cwinvestments/memstack/owasp-top10"><img src="https://agentmods.dev/badge/skills/cwinvestments/memstack/owasp-top10/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/cwinvestments/memstack/owasp-top10"><img src="https://agentmods.dev/badge/skills/cwinvestments/memstack/owasp-top10.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Memory Poisoning · line 111 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00069 | $0.04792 |
| Opus 5.5 | $0.00028 | $0.01917 |
| Sonnet 5.5 | $0.00014 | $0.00958 |
| Haiku 4.5 | $0.00007 | $0.00479 |
Grade A, and why
memstack-security-owasp-top10 scanned grade A with 2 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Search for `fetch(`, `axios.get`, `axios.post`, `got(`, `request(` calls. For each, check if the URL comes from user input (query params, request body, database). Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
Search for shell execution imports (`child_process`) and calls (`execSync`, `spawn`). Verify user input is never passed to shell commands. Use `execFile` with argument arrays instead. How it starts
The opening of the file, as written. The whole thing — 445 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🛡️ OWASP Top 10: Running Full Vulnerability Assessment...
Audit a web application against the OWASP Top 10 (2021) vulnerability categories with actionable findings and remediation.
Activation
When this skill activates, output:
🛡️ OWASP Top 10: Running Full Vulnerability Assessment...
Then execute the protocol below.
Context Guard
| Context | Status |
|---|---|
| User asks for OWASP/security audit | ACTIVE: full assessment |
| User asks for vulnerability check | ACTIVE: full assessment |
| Pre-launch security review | ACTIVE: full assessment |
| User asks about a specific OWASP category | ACTIVE, targeted check for that category |
| User is actively fixing a vulnerability | DORMANT: let them work |
Scan Modes
This skill supports two modes. Default to deep scan unless the user specifies otherwise.
| Mode | Scope | When to use |
|---|---|---|
| Quick scan | A01 (auth), A05 (headers + config), A06 (deps) | Fast pre-deploy check, CI pipeline gate, or first-pass triage |
| Deep scan | All 10 categories | Pre-launch review, security audit, compliance check |
If the user says "quick OWASP", "quick security check", or "fast scan", run only A01 + A05 + A06 and output the scorecard with the other 7 categories marked as "⏭️ SKIPPED (quick mode)".
Protocol
Run each of the 10 checks below (or A01 + A05 + A06 only in quick mode). For each, search the codebase for vulnerability patterns, classify findings, and record results for the final scorecard.
Finding format: Every finding MUST include a file path and line number in the format file:line. If a finding is project-wide (e.g., "no rate limiting anywhere"), reference the most relevant file where the fix would be applied. Vague findings like "missing HSTS" without pointing to the middleware or config file are not actionable.
A01: Broken Access Control
Risk: Users acting beyond their intended permissions: accessing other users' data, elevating privileges, or bypassing access restrictions.
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 e3de86e80759
- 1mo ago First seen · 445 lines · 69 tokens per session scan A db8ac3bff1a1
memstack-security-owasp-top10 is a skill published in the GitHub repository cwinvestments/memstack (427 stars, last pushed 5d ago), licensed MIT. It adds 69 tokens to every session and 4,792 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
puppeteer-automation
Expert guidance for browser automation using Puppeteer with best practices for web scraping, testing, screenshot capture, and JavaScript execution in headless Chrome.
rtl-internationalization
Right-to-left (RTL) layout and bidirectional text support for Hebrew, Arabic, Persian, and Urdu interfaces. Use when building UI that must support RTL languages, converting physical CSS/Tailwind properties to logical ones, handling mixed-direction (bidi) text, mirroring directional icons, or testing an app with…
gitlab-workflow
GitLab best practices for merge requests, CI/CD pipelines, issue tracking, and DevOps workflows.
gsap
Expert guidelines for building high-performance animations with GSAP (GreenSock Animation Platform).
data-analysis-jupyter
Expert guidance for data analysis, visualization, and Jupyter Notebook development with pandas, matplotlib, seaborn, and numpy.
agent-flutter-developer
Specialist subagent: Flutter/Dart cross-platform development, Riverpod state management, and platform channels specialist. Use when building Flutter apps, implementing state management, or working with native platform features. Trigger phrases: Flutter, Dart, Riverpod, Bloc, widget, MaterialApp, GoRouter, platform…