Runs Hadolint (Dockerfile linter) and returns structured diagnostics (file, line, rule, severity, message).
AI agents invoke hadolint to trigger actions in Http. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool runs an external program (Hadolint) on a Dockerfile. While it is read-only in terms of data modification (it only returns diagnostics), it executes an external process whose behavior depends on the file path argument supplied. This qualifies as Execute. Severity is medium because misuse could point the linter at unintended files or be used to probe file system paths, though it cannot modify data.
From the tool's definition 'Runs Hadolint (Dockerfile linter)' — explicitly executes an external linter tool against a file
Documented attack patterns abuse exactly the kind of access hadolint gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Http, and nothing reaches the server without passing your rules. This is the rule we recommend for hadolint:
{
"version": "1",
"default": "deny",
"tools": {
"hadolint": {
"limits": [
{
"counter": "hadolint_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}hadolint stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Runs Hadolint (Dockerfile linter) and returns structured diagnostics (file, line, rule, severity, message). It is categorised as a Execute tool in the Http MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Http MCP server in PolicyLayer and add a rule for hadolint: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Http. Nothing to install.
hadolint is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the hadolint rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for hadolint. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
hadolint is provided by the Http MCP server (@paretools/http). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Http, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
202 Http tools catalogued and risk-classified — across an index of 43,000+ MCP servers.