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-cache-poisongit 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-cache-poison)<a href="https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/hunt-cache-poison"><img src="https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/hunt-cache-poison/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-cache-poison"><img src="https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/hunt-cache-poison.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.03473 |
| Opus 5 | $0.00015 | $0.01736 |
| Sonnet 5 | $0.00006 | $0.00695 |
| Haiku 4.5 | $0.00003 | $0.00347 |
Grade A, and why
hunt-cache-poison 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -I "https://target.com/page" | grep -i "age\|x-cache\|cf-cache" How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crown Jewel Targets
Cache poisoning is high-value because a single poisoned cache entry can affect thousands or millions of victims simultaneously — one request, mass exploitation. Payout scales with blast radius.
Highest-value targets:
- CDN-served assets (cdn.shopify.com, cloudfront distributions, Fastly/Akamai edges) — poisoning these affects every visitor globally
- E-commerce platforms with affiliate/referral flows (Shopify, WooCommerce storefronts) — session hijack or affiliate fraud potential
- Gaming platforms with update servers (rockstargames updates.* domains) — DoS on update delivery = widespread client breakage
- Authentication endpoints served through caches — leads to account takeover (the highest severity variant)
- Asset CDNs (JS/CSS delivery) — XSS payload delivery at scale
- SaaS multi-tenant platforms — one poisoned response bleeds into all tenants sharing a cache key
Asset types that pay most: CDN hostnames, subdomain-per-tenant patterns, update/download servers, login/account pages cached incorrectly, affiliate link shorteners.
Attack Surface Signals
URL patterns to look for:
cdn.,assets.,static.,updates.,downloads.subdomains- URL path structures with extensions that look static:
/path/to/page.css,/account.php/nonexistent.jpg - Affiliate/link shortener endpoints:
/link/,/go/,/ref/,/out/ - Paths that mix dynamic content with cacheable-looking URLs
Response headers that signal a cache:
X-Cache: HIT / MISS
X-Cache-Status: HIT
CF-Cache-Status: HIT / MISS (Cloudflare)
Age: <nonzero>
Via: 1.1 varnish / cloudfront / fastly
Cache-Control: public, max-age=...
Surrogate-Control: max-age=...
X-Served-By: cache-...
JS/tech stack signals:
- Fastly, Varnish, Cloudfront, Akamai, Nginx proxy_cache in response headers
- Shopify/Linkpop stacks with third-party integrations
- Platforms using path-based routing without normalizing trailing segments
- Servers that reflect unvalidated headers into responses (Host, X-Forwarded-Host, X-Original-URL)
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 · 253 lines · 31 tokens per session scan A f9f0e5e74332
hunt-cache-poison is a skill published in the GitHub repository adriannoes/awesome-agentic-ai (57 stars, last pushed 13d ago), licensed MIT. It adds 31 tokens to every session and 3,473 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
importing-a-codebase
Use when the repo holds real source code but no specs: the existing-codebase branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for empty workspaces (starting-a-new-project) or feature work in a specced project (brainstorming).
starting-a-new-project
Use when the workspace is empty — no code yet — and the user brings a raw idea: the brand-new branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for features in an existing project — use brainstorming instead.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
spec-graph
The project's specs are its ground truth: durable documents describing the architecture, decisions, contracts, and boundaries behind the code, organized as a connected graph. Read this skill and reach for the spec tools FIRST — before reading code — whenever you explore the project, plan or start a task, add or change…
brainstorming
Use this BEFORE any creative or feature work: building a new feature, adding functionality, changing behavior, or making a nontrivial design decision. Turns the user's request into a validated design — recorded as a spec-graph task-spec — before any implementation. Do not skip this because a change looks small.