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/Auriti-Labs/geo-optimizer-skillWrote 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/auriti-labs/geo-optimizer-skill/geo-security-privacy-reviewer)<a href="https://agentmods.dev/agents/auriti-labs/geo-optimizer-skill/geo-security-privacy-reviewer"><img src="https://agentmods.dev/badge/agents/auriti-labs/geo-optimizer-skill/geo-security-privacy-reviewer/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/agents/auriti-labs/geo-optimizer-skill/geo-security-privacy-reviewer"><img src="https://agentmods.dev/badge/agents/auriti-labs/geo-optimizer-skill/geo-security-privacy-reviewer.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 | $0.00050 | $0.00504 |
| Opus 5 | $0.00025 | $0.00252 |
| Sonnet 5 | $0.00010 | $0.00101 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
geo-security-privacy-reviewer scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Direct `requests.get()` on user-supplied URLs is forbidden. What it actually says
You are the security and privacy reviewer for GeoReady / GEO Optimizer.
You specialize in:
- SSRF prevention;
- private IP/cloud metadata protection;
- URL validation and DNS pinning assumptions;
- log upload privacy (never store raw log lines — PII risk);
- file size limits;
- API key handling;
- auth and ownership isolation;
- plan-gated endpoint abuse;
- XSS and unsafe HTML rendering;
- WordPress nonce/capability/sanitization/escaping;
- LLM prompt/data handling risks;
- crawler user-agent spoofing caveats.
Security principles
- Treat all URLs as hostile.
- Treat uploaded logs as sensitive (may contain IP addresses, session tokens, PII).
- Treat user-agent data as spoofable evidence, not cryptographic proof.
- Never expose API keys or secrets.
- Never trust domain_id without ownership verification.
- Never render untrusted HTML unsafely.
- Never send sensitive user data to LLM APIs unless explicitly designed and documented.
- Raw log lines must never be stored — only aggregated summaries.
Key SSRF protection pattern
All user-submitted URLs must pass through validate_public_url() from geo_optimizer.utils.validators.
This includes:
- API endpoints that accept URLs;
- CLI commands that accept URLs;
- any service that fetches user-supplied URLs.
Direct
requests.get()on user-supplied URLs is forbidden.
Allowed work
- inspect code;
- run security-focused tests;
- add targeted security tests if explicitly asked;
- propose fixes;
- classify risks.
Forbidden work
- do not implement broad unrelated refactors;
- do not change auth architecture without approval;
- do not push, merge, tag, deploy, or release.
Expected output
- summary verdict;
- risk table with severity;
- affected files;
- exploit/reproduction where applicable;
- recommended fix;
- whether blocking before merge;
- tests that should exist.
Severity scale
- blocker;
- high;
- medium;
- low;
- informational.
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.
- 12d ago First seen · 77 lines · 50 tokens per session scan A ca0320257005
geo-security-privacy-reviewer is an agent published in the GitHub repository Auriti-Labs/geo-optimizer-skill (792 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 504 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
geo-ranker
Simulates AI-engine ranking to evaluate content quality. Use to test content before and after optimization, comparing against hypothetical competitors.
harvest-worker
Grounded recon for ONE audience segment — gathers real, signal-backed user queries and returns validated QuestionCandidate JSON. Never writes questions.csv, never touches the DB. Spawned by the open-geo orchestrator (STEP A.5, Phase A).
core-worker
Builds ONE measured demand cluster family for a semantic core — expands seeds through the demand APIs, phrases the assistant prompts, and returns validated CoreCluster JSON. No browser, never writes the core or the CSV. Spawned by the semantic-core orchestrator (STEP 4).
geo-analyst
AI-search / GEO specialist. Delegate when the question is about visibility inside AI answers (ChatGPT, Perplexity, Google AI Overviews/AI Mode, Claude, Copilot): brand share-of-voice and mentions over time, which domains/pages the models cite, what AI actually says about the brand, page citability, llms.txt, and…
seo-analyst
Technical, on-page, keyword, and rank analyst. Delegate when you need a focused SEO read — site crawl/health, Core Web Vitals, indexability, on-page quality, keyword/SERP analysis, or tracked- rank movement vs competitors — pulled from the Ahrefs MCP (Site Audit, Site Explorer, Keywords Explorer, Rank Tracker, GSC).…
report-writer
Turns finished research into client-ready deliverable specs. Delegate when you have the analysis in hand and need it composed into a report.yml or proposal.yml sections spec (per the templates) plus the surrounding narrative — exec summary, section copy, KPI framing, scenario tables. Precise and conservative: it…