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 datit309/supergraph --skill vibesecgit clone --depth 1 https://github.com/datit309/supergraphWrote 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/datit309/supergraph/vibesec)<a href="https://agentmods.dev/skills/datit309/supergraph/vibesec"><img src="https://agentmods.dev/badge/skills/datit309/supergraph/vibesec/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/datit309/supergraph/vibesec"><img src="https://agentmods.dev/badge/skills/datit309/supergraph/vibesec.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 | $0.00051 | $0.05936 |
| Opus 5.5 | $0.00020 | $0.02374 |
| Sonnet 5.5 | $0.00010 | $0.01187 |
| Haiku 4.5 | $0.00005 | $0.00594 |
Grade C, and why
vibesec scanned grade C 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.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
- AWS: `169.254.169.254` 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.
| Filename injection | `; rm -rf /` in filename | Sanitize filenames, use random names | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
This is a copy
94% identical to VibeSec-Skill — 21 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 — 776 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/supergraph:vibesec
Defensive security & vulnerability prevention framework. Approach code from a bug hunter's perspective to catch security vulnerabilities before production.
Announce: "🛡️ /supergraph:vibesec — enforcing security standards & vulnerability checks..."
When to Use
- Writing or reviewing web endpoints, API routes, and database queries
- Implementing authentication, session management, or JWT handling
- Creating state-changing operations (POST/PUT/PATCH/DELETE) requiring CSRF or authorization checks
- Handling user input, uploads, redirects, or outbound network requests (SSRF prevention)
- Pre-merge security audits and vulnerability prevention
Secure Coding Guide for Web Applications
Overview
This guide provides comprehensive secure coding practices for web applications. As an AI assistant, your role is to approach code from a bug hunter's perspective and make applications as secure as possible without breaking functionality.
Key Principles:
- Defense in depth: Never rely on a single security control
- Fail securely: When something fails, fail closed (deny access)
- Least privilege: Grant minimum permissions necessary
- Input validation: Never trust user input, validate everything server-side
- Output encoding: Encode data appropriately for the context it's rendered in
Access Control Issues
Access control vulnerabilities occur when users can access resources or perform actions beyond their intended permissions.
Core Requirements
For every data point and action that requires authentication:
-
User-Level Authorization
- Each user must only access/modify their own data
- No user should access data from other users or organizations
- Always verify ownership at the data layer, not just the route level
-
Use UUIDs Instead of Sequential IDs
- Use UUIDv4 or similar non-guessable identifiers
- Exception: Only use sequential IDs if explicitly requested by user
-
Account Lifecycle Handling
- When a user is removed from an organization: immediately revoke all access tokens and sessions
- When an account is deleted/deactivated: invalidate all active sessions and API keys
- Implement token revocation lists or short-lived tokens with refresh mechanisms
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 · 776 lines · 51 tokens per session scan C 87ba18a2038a
vibesec is a skill published in the GitHub repository datit309/supergraph (23 stars, last pushed 7d ago), licensed MIT. It adds 51 tokens to every session and 5,936 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (cloud metadata endpoint, recursive force delete). It is 94% identical to VibeSec-Skill, differing in 21 lines, and is treated as a copy.
vibesec compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vibesecdatit309/supergraph | Skill | 23 | 7d ago | MIT | C | 51 | Claude Code |
| arch-reviewramboz/jig | Skill | 7 | 11d ago | MIT | A | 207 | Claude Code |
| security-reviewramboz/jig | Skill | 7 | 11d ago | MIT | A | 147 | Claude Code |
| pr-reviewramboz/jig | Skill | 7 | 11d ago | MIT | A | 183 | Claude Code |
| understand-diffEgonex-AI/Understand-Anything | Skill | 91k | 11d ago | MIT | A | 27 | Claude Code |
| security-architecture-reviewcbrock84/headcount | Skill | 2.6k | 19d ago | MIT | A | 78 | Claude Code |
| code-reviewera-pavithraa/springboot-skills-marketplace | Skill | 80 | 2d ago | MIT | A | 105 | Claude Code |