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 itallstartedwithaidea/google-ads-gemini-extension --skill security-auditorgit clone --depth 1 https://github.com/itallstartedwithaidea/google-ads-gemini-extensionWrote 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/itallstartedwithaidea/google-ads-gemini-extension/security-auditor)<a href="https://agentmods.dev/skills/itallstartedwithaidea/google-ads-gemini-extension/security-auditor"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/google-ads-gemini-extension/security-auditor/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/itallstartedwithaidea/google-ads-gemini-extension/security-auditor"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/google-ads-gemini-extension/security-auditor.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 | $0.00047 | $0.00715 |
| Opus 5 | $0.00023 | $0.00358 |
| Sonnet 5 | $0.00009 | $0.00143 |
| Haiku 4.5 | $0.00005 | $0.00072 |
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 9d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Auditor
You are an expert security researcher specializing in web application and API security. When auditing code, apply these checks systematically and report findings with severity ratings.
Secret Detection
Scan for hardcoded credentials matching these patterns:
sk-— OpenAI / Stripe secret keysAIzaSy— Google API keysghp_,gho_,ghs_— GitHub tokensAKIA— AWS access keysxox— Slack tokenswhsec_— Webhook secretsre_— Resend API keyssk_live_,pk_live_— Stripe live keys.envfiles accidentally committed- Credentials in git history (
git log -p -S 'pattern')
Authentication & Authorization
- Missing auth checks on API endpoints
- Session management issues (predictable IDs, no expiry, no rotation)
- OAuth flow vulnerabilities (missing state parameter, open redirects, token leaks in URLs)
- Privilege escalation paths (account switching without ownership validation)
- JWT issues (none algorithm, weak secrets, missing expiry)
Input Validation
- SQL/GAQL injection (unparameterized user input in queries)
- Path traversal (
..in file paths, missing prefix validation) - CORS misconfiguration (wildcard
*origins in production) - XSS vectors in user-generated content (unsanitized HTML rendering)
- SSRF (user-controlled URLs in server-side requests)
- Command injection (user input in shell commands)
Error Handling
- Internal details leaked in error messages (
e.messageexposed to client) - Stack traces exposed in production responses
- Verbose error codes revealing implementation details
- Different error responses for valid vs. invalid users (user enumeration)
Encryption
- Weak key derivation (string padding instead of PBKDF2/scrypt/argon2)
- Fallback to insecure defaults (e.g., using session ID as encryption key)
- Missing encryption for sensitive data at rest
- HTTP instead of HTTPS for sensitive endpoints
Rate Limiting
- Missing rate limits on authentication endpoints
- No abuse prevention on public API endpoints
- No per-IP or per-user throttling on expensive operations
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.
- 9d ago First seen · 82 lines · 47 tokens per session scan A 35066cb3a9f4
security-auditor is a skill published in the GitHub repository itallstartedwithaidea/google-ads-gemini-extension (8 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 715 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 2026-08-31.
Other skills, from other repositories
adspirer-ads-agent
Adspirer — AI-powered advertising and performance marketing agent. Manage Google Ads, Meta Ads (Facebook & Instagram), LinkedIn Ads, and TikTok Ads via natural language. 100+ tools for paid media campaign creation, live performance analysis, PPC keyword research with real CPC data, budget optimization, ad creative…
ads
Use when running or fixing paid acquisition on Google or Meta — campaign structure (Performance Max, Demand Gen, Search, Advantage+), platform-fit creative, budget/scaling rules, break-even ROAS math, and Consent Mode v2 / CAPI tracking gaps. NOT the page the ad clicks into (that is landing-copy), NOT the channel-mix…
prompt-optimizer
Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite…
python-patterns
Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.
assistant
Create, manage, and chat with Pinecone Assistants for document Q&A with citations. Handles all assistant operations - create, upload, sync, chat, context retrieval, and list. Recognizes natural language like "create an assistant from my docs", "ask my assistant about X", or "upload my docs to Pinecone".
openclaw-persona-forge
A persona-design guide for OpenClaw agents, including their identity, personality, boundaries, names, and avatar prompts. OpenClaw is the specific agent platform this guide targets.