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 adriannoes/awesome-agentic-ai --skill hunt-business-logicgit clone --depth 1 https://github.com/adriannoes/awesome-agentic-aiWrote 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/adriannoes/awesome-agentic-ai/hunt-business-logic)<a href="https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/hunt-business-logic"><img src="https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/hunt-business-logic/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/adriannoes/awesome-agentic-ai/hunt-business-logic"><img src="https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/hunt-business-logic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 73 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 109 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00031 | $0.03022 |
| Opus 5 | $0.00015 | $0.01511 |
| Sonnet 5 | $0.00006 | $0.00604 |
| Haiku 4.5 | $0.00003 | $0.00302 |
Grade A, and why
hunt-business-logic 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST https://target.com/api/subscribe \ How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crown Jewel Targets
Business logic vulnerabilities pay highest in platforms where financial transactions, identity verification, and access controls intersect with real-world consequences. The richest targets are:
- E-commerce & payment platforms (Valve/Steam, Shopify) — payment flow manipulation, free goods, price tampering
- Marketplace & gig economy apps (Airbnb, Uber) — identity/verification bypass enabling fraud or unsafe interactions
- SaaS with tiered access (Mozilla Monitor) — bypassing verification to unlock monitoring features without entitlement
- High-traffic consumer apps (Snapchat, Yelp) — rate-limit bypass enabling spam, enumeration, or abuse at scale
Asset types that pay: checkout flows, subscription endpoints, callback/verification systems, webhook handlers, employee/internal portals exposed to the internet, and any endpoint that trusts client-supplied data to make authorization decisions.
Attack Surface Signals
URL patterns to watch:
/checkout,/order,/subscribe,/payment,/verify,/confirm,/callback/internal,/employee,/summit,/staff,/admin— internal pages accidentally public/api/v*/payment,/api/v*/notify,/webhook— payment provider callbacks- Endpoints accepting
X-Forwarded-For,X-Real-IP,CF-Connecting-IPheaders
Response/header signals:
Set-Cookiewith unvalidated session state tied to cart or order data- Payment provider names in responses:
Smart2Pay,Stripe,PayPal,Braintree - Redirect chains through third-party payment pages (in-flight data opportunity)
200 OKon subscription/verification endpoints with no CAPTCHA or token
JS patterns:
- Hardcoded internal URLs in frontend bundles (
/employee/,/staff/,/internal/) - Client-side price calculation before server submission
- Verification logic that only checks on the frontend (
if (verified) { ... }) fetch('/api/subscribe', { method: 'POST', body: ... })with no anti-CSRF token or rate-limit token
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 · 199 lines · 31 tokens per session scan A 2a8022e84ffb
hunt-business-logic is a skill published in the GitHub repository adriannoes/awesome-agentic-ai (57 stars, last pushed 14d ago), licensed MIT. It adds 31 tokens to every session and 3,022 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
alibaba-supplier-outreach
Codex-native supplier sourcing and outreach workflow for Alibaba using LaunchFast research. Use when the user wants supplier shortlists, outreach messages, reply triage, or negotiation support. Requires supplierresearch. Browser automation is optional but useful when the user wants Codex to interact with Alibaba…
kunze-ad-setup
Codex-native Amazon PPC setup workflow using Kunze's broader ecosystem-driven strategy. Use when the user wants LaunchFast-driven bulk-sheet generation with broad and phrase coverage, gap analysis, and a campaign package written to disk.
launchfast-full-research-loop
End-to-end Codex-native Amazon FBA research workflow using LaunchFast MCP. Use when the user wants a single report covering product research, IP risk, supplier sourcing, and PPC keyword intelligence. Requires researchproducts, ipcheckmanage, supplierresearch, and amazonkeywordresearch.
launchfast-ppc-research
Codex-native Amazon PPC keyword research using LaunchFast MCP. Use when the user wants competitor keyword discovery, keyword tiering, or a ready-to-upload Amazon Sponsored Products bulk file from 1-15 ASINs. Requires the LaunchFast MCP tool amazonkeywordresearch.
product-research
Deep Codex-native Amazon FBA product validation using LaunchFast MCP and the LegacyX criteria. Use when the user wants a serious viability review for a keyword, niche, or adjacent niche expansion.
wilco-ad-setup
Codex-native Amazon PPC setup workflow using Wilco's exact-match and analytics-first strategy. Use when the user wants stricter keyword control, exact-match campaigns, and a LaunchFast-driven bulk-sheet export.