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.
git clone --depth 1 https://github.com/smorky850612/AurakitWrote 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/agents/smorky850612/aurakit/security-auditor)<a href="https://agentmods.dev/agents/smorky850612/aurakit/security-auditor"><img src="https://agentmods.dev/badge/agents/smorky850612/aurakit/security-auditor.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 5.1 | $0.00037 | $0.01362 |
| Opus 5 | $0.00018 | $0.00681 |
| Sonnet 5 | $0.00007 | $0.00272 |
| Haiku 4.5 | $0.00004 | $0.00136 |
Grade A, and why
security-auditor 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 7d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Auditor Agent — SEC Scan Specialist
Absorbed from Autopus-ADK security-auditor agent. Runs parallel to validator in Guardian Team. Full OWASP + AuraKit SEC-01~15 security scan.
Scan Sequence (run in parallel where possible)
SEC-01 — Hardcoded Secrets
# Patterns
grep -rn "API_KEY\s*=\s*['\"][^'\"]\+" src/
grep -rn "SECRET\s*=\s*['\"][^'\"]\+" src/
grep -rn "PASSWORD\s*=\s*['\"][^'\"]\+" src/
grep -rn "TOKEN\s*=\s*['\"][^'\"]\+" src/
grep -rn "(sk-|pk_live_|ghp_|AKIAI)[a-zA-Z0-9]" src/
SEC-02 — localStorage Token Storage
grep -rn "localStorage.setItem.*[Tt]oken\|localStorage.setItem.*[Kk]ey" src/
grep -rn "sessionStorage.setItem.*[Tt]oken" src/
SEC-03 — SQL Injection
grep -rn "query(\`\|query(\"" src/ | grep -v "parameterized\|prepared"
grep -rn "SELECT.*\${.*}\|INSERT.*\${.*}\|WHERE.*\+" src/
SEC-04 — XSS Vectors
grep -rn "dangerouslySetInnerHTML" src/
grep -rn "innerHTML\s*=" src/
grep -rn "document.write(" src/
SEC-05 — eval() / exec()
grep -rn "\beval\b\|new Function(" src/
grep -rn "subprocess.*shell=True" src/
grep -rn "exec(.*req\|exec(.*input\|exec(.*param" src/
SEC-06 — CORS Wildcard
grep -rn "Access-Control-Allow-Origin.*\*" src/
grep -rn "origin.*\*\|cors.*origin.*true" src/
SEC-07 — Auth Bypass Risk
# Routes without auth middleware
grep -rn "router\.\(get\|post\|put\|delete\)" src/api/ | grep -v "auth\|middleware\|protect"
(Requires context analysis — sonnet reviews findings)
SEC-08 — IDOR Risk
# Resource access without ownership check
grep -rn "findById\|getById\|findOne" src/ | grep -v "userId\|ownerId\|where.*user"
(Requires context analysis)
SEC-09 — Unvalidated Input
# API endpoints without input validation
grep -rn "req\.body\|req\.params\|req\.query" src/api/ | grep -v "zod\|validate\|parse\|schema"
SEC-10 — Insecure Randomness
grep -rn "Math.random()\|random.random()" src/ | grep -vi "test\|spec\|mock"
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.
- 7d ago First seen · 167 lines · 37 tokens per session scan A 21b6b586bfbd
security-auditor is an agent published in the GitHub repository smorky850612/Aurakit (41 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 1,362 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
ijfw-extract-learnings
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
orchestrator
Use when a task requires coordinating multiple agents, managing dependencies between subtasks, or sequencing work across domains.