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 agentmods add skills/avinashp/agentsatlas/security-auditnpx skills add AvinashP/AgentsAtlas --skill security-auditgit clone --depth 1 https://github.com/AvinashP/AgentsAtlasWrote 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/avinashp/agentsatlas/security-audit)<a href="https://agentmods.dev/skills/avinashp/agentsatlas/security-audit"><img src="https://agentmods.dev/badge/skills/avinashp/agentsatlas/security-audit.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.01337 |
| Opus 5 | $0.00014 | $0.00668 |
| Sonnet 5 | $0.00006 | $0.00267 |
| Haiku 4.5 | $0.00003 | $0.00134 |
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 4d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Audit Skill
Systematically audit code for common security vulnerabilities.
Workflow
1. Identify Attack Surface
Map entry points:
- API endpoints
- User input forms
- File uploads
- URL parameters
- Headers and cookies
- WebSocket messages
# Find API routes
grep -r "app.get\|app.post\|router\." --include="*.ts" --include="*.js"
# Find form handlers
grep -r "onSubmit\|handleSubmit" --include="*.tsx" --include="*.jsx"
2. Check OWASP Top 10
Go through each category systematically:
| # | Category | What to Check |
|---|---|---|
| 1 | Broken Access Control | Auth checks on all endpoints |
| 2 | Cryptographic Failures | Sensitive data exposure |
| 3 | Injection | User input in queries/commands |
| 4 | Insecure Design | Business logic flaws |
| 5 | Security Misconfiguration | Default configs, headers |
| 6 | Vulnerable Components | Outdated dependencies |
| 7 | Auth Failures | Weak passwords, session issues |
| 8 | Data Integrity Failures | Unverified updates, CI/CD |
| 9 | Logging Failures | Missing audit trails |
| 10 | SSRF | Server-side request forgery |
3. Review Code Patterns
Search for dangerous patterns:
# SQL injection risks
grep -r "query.*\${" --include="*.ts"
grep -r "execute.*+" --include="*.py"
# Command injection risks
grep -r "exec\|spawn\|system" --include="*.ts" --include="*.js"
# XSS risks
grep -r "innerHTML\|dangerouslySetInnerHTML" --include="*.tsx"
# Hardcoded secrets
grep -r "password\|secret\|api_key\|token" --include="*.ts" --include="*.env*"
4. Check Dependencies
# JavaScript
npm audit
npx snyk test
# Python
pip-audit
safety check
5. Document Findings
For each vulnerability:
- Severity (Critical/High/Medium/Low)
- Location (file:line)
- Description
- Proof of concept (if safe)
- Recommended fix
Quick Reference
Common Vulnerabilities
Injection (SQL, NoSQL, Command, LDAP)
Vulnerable:
// SQL injection
const query = `SELECT * FROM users WHERE id = ${userId}`;
// Command injection
exec(`convert ${userFilename} output.png`);
// NoSQL injection
User.find({ username: req.body.username });
What ships with it
2 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.
- 4d ago First seen · 227 lines · 28 tokens per session scan A f83f73db50e8
security-audit is a skill published in the GitHub repository AvinashP/AgentsAtlas (7 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 1,337 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other skills, from other repositories
vibe-research
Deep research and market validation for app ideas. Use when starting a new project, validating an idea, or when the user says "research my idea", "validate my app", or "help me start a new project".
trellis-brainstorm
Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex…
trellis-session-insight
Reach into past AI conversation history through the trellis mem CLI. Use whenever the user asks 'how did we solve X last time', 'have we discussed this before', 'what was the decision on X', 'remind me what we did in this task', '上次怎么解的', '之前讨论过吗', '想起一段对话', or when starting a brainstorm that overlaps prior work…
trellis-channel
Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.
kn-research
Use when you need to understand existing code, find patterns, search project knowledge, investigate current external facts, or explore a large codebase before implementation.
trellis-finish-work
Wrap up the current session: verify quality gate passed, remind user to commit, archive completed tasks, and record session progress to the developer journal. Use when done coding and ready to end the session.