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 nxtg-ai/forge-plugin --skill owasp-securitygit clone --depth 1 https://github.com/nxtg-ai/forge-pluginWrote 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/nxtg-ai/forge-plugin/owasp-security)<a href="https://agentmods.dev/skills/nxtg-ai/forge-plugin/owasp-security"><img src="https://agentmods.dev/badge/skills/nxtg-ai/forge-plugin/owasp-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/nxtg-ai/forge-plugin/owasp-security"><img src="https://agentmods.dev/badge/skills/nxtg-ai/forge-plugin/owasp-security.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 | $0.00185 | $0.04657 |
| Opus 5.5 | $0.00074 | $0.01863 |
| Sonnet 5.5 | $0.00037 | $0.00931 |
| Haiku 4.5 | $0.00018 | $0.00466 |
Grade C, and why
OWASP Security scanned grade C with 5 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
was blocked by a Forge guard (rm -rf, chmod 777, curl|sh, force-push, eval(), Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
| A08 | Integrity Failures | `pickle.loads()`; `yaml.load()` without `SafeLoader`; `eval()`; `curl … \| bash`; missing CDN subresource integrity | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
was blocked by a Forge guard (rm -rf, chmod 777, curl|sh, force-push, eval(), Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
was blocked by a Forge guard (rm -rf, chmod 777, curl|sh, force-push, eval(), Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
os.system, shell=True, string-concat SQL, reading .env/*.pem/*.key). Covers OWASP How it starts
The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OWASP Security Knowledge
Detection-first reference for security-sensitive code review, and the operating
guide to the Forge plugin's own security guards. The tables below are the triage
layer — one detection signal per category, kept inline so this skill is useful the
moment it preloads into the security agent. When a signal fires, open the matching
reference/*.md for the vulnerable→fixed code.
This skill covers guidance for any stack a Forge user builds in (TypeScript/JS, Python, Rust, Go, …). Examples are illustrative, not tied to any one codebase.
How to use this skill
- Scan the diff/codebase against the detection signals below (grep the patterns).
- On a hit, open the linked reference for the remediation pattern.
- Before reporting, run the Security Review Checklist (§ below).
- Filter results through False Positive Filters — do not report noise.
- If a write/command was blocked by a Forge guard, jump to Forge security controls for the reason + correct fix.
OWASP Top 10:2025 — detection signals
Full vulnerable→fixed code: reference/owasp-top10.md.
| ID | Category | Grep for |
|---|---|---|
| A01 | Broken Access Control | routes without auth middleware; queries using user IDs with no ownership filter; missing role checks; origin: "*" |
| A02 | Cryptographic Failures | secret|password|key|token literals in source (not env); MD5/SHA1 on passwords; Math.random()/random.random() for security; verify=False; rejectUnauthorized: false |
| A03 | Injection | string concatenation in queries; exec()/eval() with user input; render_template_string(); $where in Mongo; unsanitized innerHTML |
| A04 | Insecure Design | no rate limit on auth; predictable reset tokens; client-only validation; no lockout; no re-auth on privilege change |
| A05 | Security Misconfiguration | origin: "*"; missing helmet()/headers; DEBUG=true in prod; stack traces in responses; directory listing |
| A06 | Vulnerable Components | run npm audit --production / pip-audit / cargo audit; unpinned or unmaintained deps |
| A07 | Auth Failures | password min length < 8; sessions in URLs; no rate limit on /login//register; plaintext passwords; missing httpOnly/secure cookie flags |
| A08 | Integrity Failures | pickle.loads(); yaml.load() without SafeLoader; eval(); curl … | bash; missing CDN subresource integrity |
| A09 | Logging Failures | no logging middleware; console.log-only; secrets/tokens in log output; no alerting on repeated auth failures |
| A10 | SSRF | fetch()/axios()/requests.get() with user-supplied URL; no hostname allowlist; no protocol restriction; no private-IP block |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 298 lines · 185 tokens per session scan C b3a3f32e42af
OWASP Security is a skill published in the GitHub repository nxtg-ai/forge-plugin (6 stars, last pushed 4d ago), licensed MIT. It adds 185 tokens to every session and 4,657 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it C with 5 findings (asks for root, downloads and executes remote code, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
rag-retrieval
Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, contextual retrieval, HyDE, agentic RAG, multimodal RAG, query decomposition, reranking, or pgvector search.
error-analysis
Evals-first error analysis for LLM apps: clusters real Langfuse or JSONL traces into a human-confirmed failure taxonomy with counts, then recommends binary pass/fail evals for recurring named modes. Use to learn what to measure before writing evals. Not for CI failures.
dev
One-command dev loop boot. Spins up portless (named HTTPS subdomain), emulate (stateful API mocks), the project's dev server, and an agent-browser session, all keyed to the current git branch. Use when starting a feature branch, switching worktrees, or returning to a project after a break. Skips silently with install…
testing-llm
LLM and AI testing patterns — mock responses, evaluation with DeepEval/RAGAS, structured output validation, and agentic test patterns (generator, healer, planner). Use when testing AI features, validating LLM outputs, or building evaluation pipelines.
accessibility
Accessibility patterns for WCAG 2.2 compliance, keyboard focus management, React Aria component patterns, cognitive inclusion, native HTML-first philosophy, and user preference honoring. Use when implementing screen reader support, keyboard navigation, ARIA patterns, focus traps, accessible component libraries…
manage-schemas
Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…