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 auditing-open-redirect-and-forced-navigationgit 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/auditing-open-redirect-and-forced-navigation)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-open-redirect-and-forced-navigation"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-open-redirect-and-forced-navigation/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/auditing-open-redirect-and-forced-navigation"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-open-redirect-and-forced-navigation.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 | $0.00162 | $0.02169 |
| Opus 5.5 | $0.00065 | $0.00868 |
| Sonnet 5.5 | $0.00032 | $0.00434 |
| Haiku 4.5 | $0.00016 | $0.00217 |
Grade A, and why
auditing-open-redirect-and-forced-navigation 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing open redirect and forced navigation: when the app sends the user wherever the URL says
An application constantly sends users onward: back to where they were after login, to a success page after an action, to an identity provider and back during authorization. When the destination comes from an untrusted parameter, a stored value, or a header, and the app redirects there without confirming it is one of its own pages, the app becomes a trusted springboard to an attacker's site. The link starts on the real domain, so it survives a glance and a mail filter, and lands on a lookalike login that harvests credentials. Worse, when the redirect carries an authorization code or a token in the URL, forcing the destination steals that secret outright. The bug is not the redirect feature; it is a destination taken from the request and trusted without an allowlist. You find it by locating every redirect and navigation and asking whether an attacker chooses where it goes.
When to use
- A return, next, redirect, callback, or continue parameter controls where a user is sent after an action.
- Client code assigns a location or writes a meta refresh from a value influenced by the request or storage.
- An authorization or single-sign-on flow returns to a URL supplied in the request and carries a code.
Scope check
Test redirect behavior only against applications you own or are authorized to assess, sending the redirect to a benign destination you control rather than a live phishing page, and never capturing a real user's token. A confirmed forced redirect that carries a token is credential theft, so keep every probe within the authorized scope. If you can't name the authorization, stop.
The loop
- Establish whether the target is checked against an allowlist first. For each redirect, determine whether the destination is confirmed to be one of the app's own pages, by an allowlist of paths or hosts matched exactly, or whether it is used as given. This is the false-positive killer: a redirect that only ever sends the user to a fixed internal path, or validates the target against an exact allowlist, is not open, while one that reflects the parameter is. Name the check before crafting a target.
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 · 138 lines · 162 tokens per session scan A 19ea0aa76c85
auditing-open-redirect-and-forced-navigation is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 162 tokens to every session and 2,169 once invoked, about $0.0006 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
playwright-skill
IMPORTANT - Path Resolution: This skill can be installed in different locations (plugin system, manual installation, global, or project-specific). Before executing any commands, determine the skill directory based on where you loaded this SKILL.md file, and use that path in all commands below.
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations, post-launch readiness and people. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line…
analyzing-malicious-url-with-urlscan
URLScan.io is a free service for scanning and analyzing suspicious URLs. It captures screenshots, DOM content, HTTP transactions, JavaScript behavior, and network connections of web pages in an isolat.
integrate-arcjet-guard-genkit
Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…
integrate-arcjet-guard-tanstack-ai
Integrate Arcjet security into a TanStack AI chat() app using @arcjet/guard — put guardMiddleware first on chat({ middleware }) so onBeforeToolCall gates tools, and read a caller-owned id from chat({ context }). Use when asked to add Arcjet to TanStack AI, rate limit its tools, screen inbound messages, or block prompt…
integrate-arcjet-guard-claude-managed-agents
Integrate Arcjet security into Claude Managed Agents (hosted REST+SSE, beta managed-agents-2026-04-01) using @arcjet/guard — screen user.message / initialevents before sessions.events.send, and gate custom tools on agent.customtooluse. Use when asked to add Arcjet to Claude Managed Agents, rate limit custom tools, or…