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-account-recovery-and-reset-trustgit 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-account-recovery-and-reset-trust)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-account-recovery-and-reset-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-account-recovery-and-reset-trust/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-account-recovery-and-reset-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-account-recovery-and-reset-trust.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 | $0.00183 | $0.02137 |
| Opus 5 | $0.00092 | $0.01069 |
| Sonnet 5 | $0.00037 | $0.00427 |
| Haiku 4.5 | $0.00018 | $0.00214 |
Grade A, and why
auditing-account-recovery-and-reset-trust 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 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.
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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing account recovery and reset trust: the alternate door into every account
Every login has a back door built in on purpose: the password reset and account recovery flow. It exists so a locked-out user can get back in, which means it is, by design, a way to gain access to an account without the password. That makes it a prime takeover target, and it is frequently weaker than the front door it protects. The reset token may be guessable, long-lived, reusable, or not bound to the account, so an attacker can predict or replay it. The recovery path may verify a weaker factor than login and skip the multi-factor requirement, so recovery becomes the multi-factor bypass. The reset link's host may come from a request header an attacker controls, so the emailed token leaks to the attacker's domain. And recovery may trust an unverified email or phone change, redirecting the reset to the attacker. The audit treats recovery as an authentication path with the same rigor as login. You audit this by walking the flow and testing each trust it places.
When to use
- An application offers password reset or account recovery as a way to regain access to an account.
- Reset tokens may be weak, long-lived, reusable, or not bound to the requesting account.
- Recovery may verify a weaker factor than login, bypass multi-factor, or leak the reset link off-domain.
Scope check
Test recovery flows only against accounts and applications you own or are authorized to assess, on non-production accounts. Exercising reset attempts real credential changes, so use test accounts you control and never reset or take over an account that is not yours. If you can't name the authorization, stop.
The loop
- Establish the intended recovery assurance first. Name what proof recovery should require and that it must be at least as strong as login, including any multi-factor requirement. This is the false-positive killer: a recovery flow with a high-entropy, single-use, short-lived, account-bound token, that enforces the same factors as login and builds the link from a server-fixed host, is correct. Name the intended assurance, then test each element.
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 · 141 lines · 183 tokens per session scan A ab9444580951
auditing-account-recovery-and-reset-trust is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 183 tokens to every session and 2,137 once invoked, about $0.0009 per session on Opus 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 2026-08-31.
Other skills, from other repositories
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations and post-launch readiness. 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 citations…
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-langgraph
Integrate Arcjet security into a LangGraph Graph API agent using @arcjet/guard — wrap tool() / StructuredTool, wrap ToolNode for unwrapped MCP tools, and read threadid for correlation. Use when asked to add Arcjet to a LangGraph StateGraph / ToolNode agent, rate limit its tools, screen inbound messages, or block…
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…
linear-claude-skill
Manage Linear issues, projects, and teams.