Connect an agent without handing it the keys to your machine.
Anyone can list thousands of AI tools. The hard part is trusting them. On FindAgent, every agent you connect is held to the same rules — enforced in code, not promised on a badge. Here is exactly what those rules are and what they don’t cover.
Each one is enforced by FindAgent’s runtime and review pipeline — a creator can’t opt out.
Most agents run no code at all
A declarative agent — a recipe, a tool-using “doer”, or a skills bundle — never ships code that runs on your machine. It only describes what to do; one trusted FindAgent runtime decides how, from a fixed set of safe actions (an API call or a prompt). So connecting one can’t run someone else’s program on your computer.
What it can do
Call the specific tools it declares — read your data, or, for a “doer”, take an action you ask for.
What it can’t
Run arbitrary code, reach hosts it never declared, or touch your machine outside your AI client.
Your API keys go to one place only
When an agent needs a key — say your GitHub token — that key is bound to the exact hosts the agent declares up front. The runtime attaches it only to a request going to one of those hosts, and if a request tries to redirect the key somewhere else, the key is dropped. You can see an agent’s declared destinations on its page before you connect.
What it can do
Send your key to the destinations it lists on its page (for example, api.github.com).
What it can’t
Send your key to any other host, or hand it to the creator — you enter keys encrypted, and the creator never sees the value.
Results are scanned before you see them
Every result an agent returns is scanned for leaked secrets and prompt-injection attempts — an always-on check that an agent’s configuration cannot switch off. An agent can add stricter rules (like stripping personal data from a result), but it can never remove the baseline scan.
What it can do
Add extra guardrails on top of the baseline — never fewer.
What it can’t
Disable the mandatory secret-and-injection scan on its results.
Code agents run in a locked-down sandbox
A few agents do run the creator’s real code. Hosted code agents run it on FindAgent, in a single-use sandbox created fresh for each run and thrown away after, walled off from FindAgent’s own systems — it starts with no network access and can reach only the hosts the agent declares. A creator may also offer a code agent to run on your OWN machine (a local agent) so it can reach your local tools; that one is clearly labeled, shows its source, and asks for your consent before you download and run it — FindAgent never runs a local agent for you, and there is no sandbox around it, so review the source first.
What it can do
Run the creator’s code in isolation and reach only its declared hosts.
What it can’t
Run on your computer, reach the open internet by default, or touch FindAgent’s own app and data.
Every listing is scanned and human-reviewed
Before an agent can go live, an automated scan checks it and a person on the FindAgent team reviews it. The publish step is enforced on our servers and fails closed — anything the checks can’t verify as safe is held back rather than waved through. A published agent, review, or comment can still be reported for a second look.
What it can do
Go live only after passing the automated scan and human review.
What it can’t
Self-publish, or slip past a failed scan or a failed build.
See the facts on every agent
You don’t have to take our word for it. Each agent’s page shows a plain-language summary drawn from that agent’s own definition — whether it ships code, the exact hosts your keys can reach, and which of its tools can change or delete data. No score, just the facts.
Honest boundaries build more trust than a wall of green checkmarks. Here’s what these protections don’t cover.
We don’t claim an agent is bug-free or that its results are correct — the guarantees are about safety boundaries, not quality. Read reviews and try an agent before relying on it.
We don’t claim the secret scan stops a deliberately malicious code agent from smuggling data out — a determined program can encode around a text scan. The real boundary there is the sandbox’s network allowlist, which blocks any host the agent didn’t declare.
We don’t claim to vet the third-party services an agent connects to. If an agent calls an external API, that provider’s own security and privacy apply once your request reaches them.
We don’t rank agents by a security “score” or grade. We show you the concrete facts — what code it runs, where your keys go, what it can change — and let you decide.
For an agent listed only as a pointer to an external server the provider runs, FindAgent doesn’t run or inspect that server — you connect to it directly with the provider’s own sign-in.
Want the engineering detail?
The technical security model covers the runtime, the scan, the sandbox, and credential custody in depth.
Connect an agent without handing it the keys to your machine.
Anyone can list thousands of AI tools. The hard part is trusting them. On FindAgent, every agent you connect is held to the same rules — enforced in code, not promised on a badge. Here is exactly what those rules are, and what they don’t cover.
Each one is enforced by FindAgent’s runtime and review pipeline — a creator can’t opt out.
Most agents run no code at all
A declarative agent — a recipe, a tool-using “doer”, or a skills bundle — never ships code that runs on your machine. It only describes what to do; one trusted FindAgent runtime decides how, from a fixed set of safe actions (an API call or a prompt). So connecting one can’t run someone else’s program on your computer.
What it can do
Call the specific tools it declares — read your data, or, for a “doer”, take an action you ask for.
What it can’t
Run arbitrary code, reach hosts it never declared, or touch your machine outside your AI client.
Your API keys go to one place only
When an agent needs a key — say your GitHub token — that key is bound to the exact hosts the agent declares up front. The runtime attaches it only to a request going to one of those hosts, and if a request tries to redirect the key somewhere else, the key is dropped. You can see an agent’s declared destinations on its page before you connect.
What it can do
Send your key to the destinations it lists on its page (for example, api.github.com).
What it can’t
Send your key to any other host, or hand it to the creator — you enter keys encrypted, and the creator never sees the value.
Results are scanned before you see them
Every result an agent returns is scanned for leaked secrets and prompt-injection attempts — an always-on check that an agent’s configuration cannot switch off. An agent can add stricter rules (like stripping personal data from a result), but it can never remove the baseline scan.
What it can do
Add extra guardrails on top of the baseline — never fewer.
What it can’t
Disable the mandatory secret-and-injection scan on its results.
Code agents run in a locked-down sandbox
A few agents do run the creator’s real code. Hosted code agents run it on FindAgent, in a single-use sandbox created fresh for each run and thrown away after, walled off from FindAgent’s own systems — it starts with no network access and can reach only the hosts the agent declares. A creator may also offer a code agent to run on your OWN machine (a local agent) so it can reach your local tools; that one is clearly labeled, shows its source, and asks for your consent before you download and run it — FindAgent never runs a local agent for you, and there is no sandbox around it, so review the source first.
What it can do
Run the creator’s code in isolation and reach only its declared hosts.
What it can’t
Run on your computer, reach the open internet by default, or touch FindAgent’s own app and data.
Every listing is scanned and human-reviewed
Before an agent can go live, an automated scan checks it and a person on the FindAgent team reviews it. The publish step is enforced on our servers and fails closed — anything the checks can’t verify as safe is held back rather than waved through. A published agent, review, or comment can still be reported for a second look.
What it can do
Go live only after passing the automated scan and human review.
What it can’t
Self-publish, or slip past a failed scan or a failed build.
See the facts on every agent
You don’t have to take our word for it. Each agent’s page shows a plain-language summary drawn from that agent’s own definition — whether it ships code, the exact hosts your keys can reach, and which of its tools can change or delete data. No score, just the facts.
Honest boundaries build more trust than a wall of green checkmarks. Here’s what these protections don’t cover.
We don’t claim an agent is bug-free or that its results are correct — the guarantees are about safety boundaries, not quality. Read reviews and try an agent before relying on it.
We don’t claim the secret scan stops a deliberately malicious code agent from smuggling data out — a determined program can encode around a text scan. The real boundary there is the sandbox’s network allowlist, which blocks any host the agent didn’t declare.
We don’t claim to vet the third-party services an agent connects to. If an agent calls an external API, that provider’s own security and privacy apply once your request reaches them.
We don’t rank agents by a security “score” or grade. We show you the concrete facts — what code it runs, where your keys go, what it can change — and let you decide.
For an agent listed only as a pointer to an external server the provider runs, FindAgent doesn’t run or inspect that server — you connect to it directly with the provider’s own sign-in.
Does connecting an agent run someone else’s code on my computer?
For a declarative agent — a recipe, a tool-using doer, or a skills bundle — no. It ships no executable code; one trusted FindAgent runtime performs only the actions the agent declares. The agents that run real code are “code agents”: most run in an isolated sandbox on FindAgent, never on your machine. A creator may also offer a code agent to run on your OWN machine (a local agent) so it can reach your local tools — that one is clearly labeled, asks for your consent, and shows its source before you download and run it, exactly like installing an npm package or a local MCP server. FindAgent never runs a local agent for you.
Where do my API keys go when I connect an agent?
A key is bound to the exact hosts the agent declares. The runtime attaches it only to requests going to one of those hosts and drops it if a request tries to redirect it elsewhere. Keys are entered encrypted and the creator never sees the value. Each agent’s declared destinations are shown on its page before you connect.
Can an agent leak my secrets in its results?
Every result is scanned for leaked secrets and prompt-injection before it reaches you, and that scan cannot be turned off by an agent. It catches accidental leaks; the stronger boundary against a deliberately malicious code agent is the sandbox network allowlist, which blocks any host the agent didn’t declare.
Is every agent reviewed before it goes live?
Yes. Every listing passes an automated security scan and a human review, and the publish step is enforced on our servers and fails closed — a failed scan or build holds an agent back rather than letting it through. Published items can also be reported for a second look.