High-risk tools in Pentest Ai

High severity Pentest Ai MCP Server 29 of 52 tools

29 of the 52 tools in Pentest Ai are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.

Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.

Tools at high risk

authenticated_scan Execute

authenticated_scan
browser_inspect Execute

Inspect a URL with the headless browser.
builtin_scan Execute

builtin_scan
ensure_tools_installed Execute

ensure_tools_installed
http_request Execute

http_request
kill_process Execute

Terminate a running tool subprocess by PID.
plan_tools Execute

plan_tools
poll_oob Execute

poll_oob
prove_attack_chain Execute

prove_attack_chain
resume_engagement Execute

resume_engagement
run_probe Execute

run_probe
run_recon Execute

run_recon
run_tool Execute

Run a specific security tool against a target.
scan_dns_builtin Execute

Perform DNS enumeration (built-in).
scan_ports_builtin Execute

Scan common ports on a target (built-in, no nmap required).
select_agent Execute

select_agent
set_intensity Execute

Change scan intensity (stealth, normal, aggressive) mid-engagement.
start_campaign Execute

Start a multi-target campaign. Creates one engagement per target.
start_engagement Execute

start_engagement
test_active_directory Execute

test_active_directory
test_api_security Execute

Run API security testing (REST + GraphQL) following OWASP API Top 10.
test_cloud Execute

test_cloud
test_credentials Execute

Run authentication testing (default creds, password spray, MFA bypass).
test_mobile Execute

Run mobile app security testing (Android or iOS).
test_privesc Execute

Run privilege escalation enumeration on a compromised host.
test_social_engineering Execute

Run a social engineering assessment (phishing simulation, OSINT, DMARC audit).
test_vulnerabilities Execute

Run vulnerability scanning (Nuclei + nikto; nuclei CVE templates are the primary known-CVE path).
test_web_app Execute

test_web_app
test_wireless Execute

Run wireless security assessment (WiFi + Bluetooth). Returns

Attacks that target this class

High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.

Destructive Action Autonomy
Runaway Tool Loops
Prompt Injection via Tool Results

High-risk tools in Pentest Ai

Tools at high risk

Attacks that target this class

More on Pentest Ai

Enforce policy on every Pentest Ai tool call.