When you give an LLM a tool, you hand it a real function and let it choose the arguments. Those tools are everything your agent can do to a real system: read a file, write to your database, send an email, run a shell command, delete data. They are your risk surface, and most teams have never looked at it in one place.
So we did. We ran scan
across a batch of popular open-source TypeScript AI agents. A few of the things it found, none of them exotic:
grep
and glob
tools, which sound read-only, actually shell out through execSync
. Its bash
tool passes a model-chosen string straight to spawn
. Arbitrary command execution, behind three innocuous names.query
tool that fires an HTTP DELETE
. A "query" that deletes.calculator
that runs eval
on whatever the model types, in a widely-used agent framework. Arbitrary code execution behind the friendliest name in the box.fetch
tool aimed at whatever URL the model supplies. That is a door to your internal network (an SSRF surface).Notice the pattern. The dangerous tools are not named dangerous
. They are named grep
, query
, calculator
. A name is a claim. The code is the evidence.
scan
reads that evidence. One command, no install, no signup, no code change:
npx @agentx-core/scan .
It lists every tool the model can call and ranks each one by what it can do, from read-only up to destructive:
RISK TOOL GUARD WHY
---- ---- ------ ------------------------
high calculator yes calls `eval`
lib/tools/compute.ts:4
high grep yes calls `execSync`
lib/tools/system.ts:8
med sendEmail yes calls `mailer.send`
lib/tools/io.ts:5
med fetchUrl yes outbound req to agent-controlled host (SSRF)
lib/tools/io.ts:11
2 of 5 tools can take destructive or batch actions.
Nothing here is guarding them: no AgentX in this project's dependencies.
Every ranking carries its evidence, so you can check it instead of trusting it. Scan reads the tool's body, not its name: a tool called tidyUp
that deletes files ranks high, and a scary-sounding tool whose code is actually clean goes to "review," not the top. When it cannot tell, it says so. On one agent, all 32 tools came back "nothing here to guard" because they run elsewhere, and scan said exactly that instead of inventing risk.
It does not run your code, and it does not decide whether a tool is exploitable. It sorts an inventory so the dangerous end is the first thing you see. Expect roughly a third of a real codebase to land in "review." That is the honest cost of not guessing.
Scan reports. It does not change your code. To actually guard what it finds, put the AgentX gateway in front of your agent, or wrap your MCP server in one line. Both are language-agnostic, so there is no SDK to adopt.
It covers TypeScript agents built on the Vercel AI SDK today. Python agent? The scanner is TypeScript for now, but the guard it points to, the gateway and the MCP wrapper, is language-agnostic. Run it on yours:
npx @agentx-core/scan .
This matters more as models get better, not less. A more capable agent does more with an unguarded tool.
npx @agentx-core/scan .