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 UnboundCompute/security-agent-skills --skill hunting-http-parameter-pollutiongit clone --depth 1 https://github.com/UnboundCompute/security-agent-skillsWrote 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/unboundcompute/security-agent-skills/hunting-http-parameter-pollution)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-http-parameter-pollution"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-http-parameter-pollution/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/unboundcompute/security-agent-skills/hunting-http-parameter-pollution"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-http-parameter-pollution.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 | $0.00201 | $0.02082 |
| Opus 5.5 | $0.00080 | $0.00833 |
| Sonnet 5.5 | $0.00040 | $0.00416 |
| Haiku 4.5 | $0.00020 | $0.00208 |
Grade A, and why
hunting-http-parameter-pollution 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 1mo 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunting HTTP parameter pollution: when two parsers disagree
An HTTP request can carry the same parameter name twice, or shape a parameter as a list, and nothing in the protocol says which value wins. Each component decides on its own: one framework takes the first occurrence, another the last, a third concatenates them, a fourth exposes an array. Parameter pollution is the bug that appears when two components on the path make different choices about the same duplicated input. A gateway or a validator inspects one occurrence and approves the request; the backend that acts on the request reads a different occurrence. The value that was checked is not the value that is used. That gap bypasses a security filter, confuses an authorization or routing decision, or slips a payload past a web application firewall that examined the harmless copy. The vulnerability is entirely relational: a single parser is never wrong with itself, so the work is to find two parsers that differ and a check on one side of the difference.
When to use
- A request crosses more than one component that parses parameters (gateway, framework, backend, service).
- A security check, filter, or authorization decision reads a parameter that is also read by a later sink.
- Parameters can be duplicated or array-shaped, in the query string, the body, or both at once.
Scope check
Test parameter pollution only against systems you own or are authorized to assess, on non-production infrastructure, because a confirming request can bypass an access control or reach a privileged action. Probe with benign values and observe which occurrence is honored rather than exercising the bypass against real data. If you can't name the authorization, stop.
The loop
- Establish that two components parse duplicates differently first. Map the components a request traverses and determine how each resolves a repeated or array-shaped parameter: first wins, last wins, concatenation, array exposure, error. This is the false-positive killer: if every component on the path resolves duplicates identically, the checked value and the used value are always the same and there is no pollution bug. Name at least two components whose resolution differs before proceeding.
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.
- 1mo ago First seen · 140 lines · 201 tokens per session scan A d84866f696a0
hunting-http-parameter-pollution is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 201 tokens to every session and 2,082 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
integrate-arcjet-guard-cloudflare-think
Integrate Arcjet security into a Cloudflare Think app using @arcjet/guard — assign guardHooks().beforeToolCall on a Think subclass so the hook gates tools, and read a caller-owned id from helper options. Use when asked to add Arcjet to Cloudflare Think, @cloudflare/think, rate limit its tools, screen inbound messages…
protect
Add Arcjet request protection to JavaScript and TypeScript HTTP handlers. Use when protecting Next.js, Express, Fastify, SvelteKit, Remix, React Router, Hono, Astro, Nuxt, Bun, Deno, NestJS, or Node.js routes with rate limiting, bot detection, Shield, email validation, or sensitive info detection.
create-auth-skill
Scaffold and implement authentication in TypeScript/JavaScript apps using Better Auth. Detect frameworks, configure database adapters, set up route handlers, add OAuth providers, and create auth UI pages. Use when users want to add login, sign-up, or authentication to a new or existing project with Better Auth.
fhir-developer-skill
FHIR API development guide for building healthcare endpoints. Use when: (1) Creating FHIR REST endpoints (Patient, Observation, Encounter, Condition, MedicationRequest), (2) Validating FHIR resources and returning proper HTTP status codes and error responses, (3) Implementing SMART on FHIR authorization and OAuth…
api-security
Reviews REST and GraphQL APIs against the OWASP API Security Top 10:2023. Auto-invoked when reviewing OpenAPI/Swagger specs, API endpoint code, or GraphQL schemas. Covers BOLA, BFLA, authentication, rate limiting, and SSRF. Produces findings mapped to API1-API10 with remediation guidance.
create-auth-skill
Scaffold and implement authentication in TypeScript/JavaScript apps using Better Auth. Detect frameworks, configure database adapters, set up route handlers, add OAuth providers, and create auth UI pages. Use when users want to add login, sign-up, or authentication to a new or existing project with Better Auth.