Run cloud security assessment. Providers: aws, azure, gcp Tests for: Misconfigurations, exposed secrets, overly permissive IAM, vulnerable services, and privilege escalation paths. Recommended (secure): pass auth_profile = name of a profile that references the cloud credential (env var, op://, va...
AI agents invoke test_cloud to trigger actions in Pentest Ai. 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.
This tool actively executes security assessment operations against cloud infrastructure using real credentials. It runs external tools and probes live cloud environments (IAM, services, secrets) for vulnerabilities. On a pentesting server explicitly designed for 'autonomous pentests' with 'real security tools,' this constitutes active execution against potentially sensitive cloud infrastructure.
From the tool's definition 'Run cloud security assessment' testing for 'Misconfigurations, exposed secrets, overly permissive IAM, vulnerable services, and privilege escalation paths' across AWS, Azure, GCP providers
Documented attack patterns abuse exactly the kind of access test_cloud gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pentest Ai, and nothing reaches the server without passing your rules. This is the rule we recommend for test_cloud:
{
"version": "1",
"default": "deny",
"tools": {
"test_cloud": {
"limits": [
{
"counter": "test_cloud_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}test_cloud 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.
Run cloud security assessment. Providers: aws, azure, gcp Tests for: Misconfigurations, exposed secrets, overly permissive IAM, vulnerable services, and privilege escalation paths. Recommended (secure): pass auth_profile = name of a profile that references the cloud credential (env var, op://, vault path, AWS-SM ARN). Deprecated (insecure, removed in 0.11): credentials dict literal. It is categorised as a Execute tool in the Pentest Ai MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pentest Ai MCP server in PolicyLayer and add a rule for test_cloud: 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 Pentest Ai. Nothing to install.
test_cloud 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 test_cloud 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 test_cloud. 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.
test_cloud is provided by the Pentest Ai MCP server (0xsteph/pentest-ai). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 51 Pentest Ai tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
51 Pentest Ai tools catalogued and risk-classified — across an index of 42,500+ MCP servers.