Crawlemoon MCP Server

crawlemoon PyPI v1.1.11

Published by an unidentified publisher — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.

View on PyPI ↗ Raw report (JSON) ↗

Trust grade

61/100

Last scanned 2026-07-23

Trust

D · 61/100

Adoption risk for you: the threat score, then adjusted down for blast radius, publisher verification and how much the scan could see. Deterministic; every point is auditable.

Capability

Critical

Blast radius if it went rogue — what the server’s tools could reach. Independent of trust.

Coverage

Source

How much the scan could actually inspect. Shallow coverage is stated, never hidden.

D Why this grade threat 76 − adoption risk = 61/100

The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.

1. Threat score — 100 − 23.8 = 76. What the published surface and source actually contain:

Points	What was found	Category
−15.4	Obfuscated / encoded payload in server code MTC-SRC-004	injection
−6.3	Unsafe deserialization MTC-SRC-007	permissions
−2.1	Package has no source repository MTC-SUP-011	supply-chain

2. Client adoption risk — 76 − 15 = 61. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:

Points	Adoption-risk factor
−10	capability blast radius (critical) — client exposure if the model is manipulated
−5	publisher verification (unlocatable) — no provenance and no public repository to inspect
✓	inspection depth (source) — how much of the target the scan could see

Capability observations and info notes are shown under Findings but never scored. Open any row's finding below for the file, line and evidence behind a deduction.

Findings 55

high Obfuscated / encoded payload in server code (tests/test_js_deobfuscator.py)MTC-SRC-004

In the server's implementation (`tests/test_js_deobfuscator.py:34`): Decoding an encoded blob and executing it is how malicious logic is hidden from human review of the source. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.

Evidence: eval(atob

Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.

Location: server tests/test_js_deobfuscator.py

high Tool "execute_js" exposes command/code executionMTC-CAP-001

Tool "execute_js" appears to run shell commands or evaluate code (parameter "script"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.

Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.

Location: tool execute_js

high Dynamic code execution in server code (src/intelligence/js/deobfuscator.py)MTC-SRC-001

In the server's implementation (`src/intelligence/js/deobfuscator.py:68`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.

Evidence: eval(

Location: server src/intelligence/js/deobfuscator.py

high Dynamic code execution in server code (tests/test_js_deobfuscator.py)MTC-SRC-001

In the server's implementation (`tests/test_js_deobfuscator.py:34`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.

Evidence: eval(

Location: server tests/test_js_deobfuscator.py

high Dynamic code execution in server code (tests/test_js_security.py)MTC-SRC-001

In the server's implementation (`tests/test_js_security.py:33`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.

Evidence: eval(

Location: server tests/test_js_security.py

high Shell/command execution in server code (src/core/browser/xray.py)MTC-SRC-002

In the server's implementation (`src/core/browser/xray.py:96`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.

Evidence: subprocess.run(

Location: server src/core/browser/xray.py

high Shell/command execution in server code (src/mcp/server.py)MTC-SRC-002

In the server's implementation (`src/mcp/server.py:1325`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.

Evidence: spawn (

Location: server src/mcp/server.py

medium Untrusted input can drive an external actionMTC-FLOW-005

Untrusted-input tools ([check_robots, crawl]) co-exist with external-action tools ([deep_analyze, discover_apis, introspect_graphql, analyze_websocket, record_session, analyze_auth, detect_protection, save_session, analyze_sitemap, check_robots, take_screenshot, extract_article, solve_captcha, detect_technology, smart_extract, convert_to_markdown, stealth_request, get_rate_limit_stats, add_proxy, remove_proxy, test_proxy, execute_graphql, execute_js, get_cookies, get_storage, extract_links, extract_forms, extract_metadata, extract_tables, execute_cdp, get_dom_tree, measure_performance, analyze_resources, check_accessibility, monitor_network, fill_form, wait_and_extract, crawl, structured_extract, configure_xray_subscription, test_xray_nodes]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.

Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.

medium Hardcoded egress to an external endpoint (tests/test_js_analyzer.py)MTC-SRC-003

In the server's implementation (`tests/test_js_analyzer.py:23`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.

Evidence: fetch('https://api.example.com/users'

Location: server tests/test_js_analyzer.py

medium Hardcoded egress to an external endpoint (tests/test_mcp_server.py)MTC-SRC-003

In the server's implementation (`tests/test_mcp_server.py:115`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.

Evidence: fetch('https://api.example.com'

Location: server tests/test_mcp_server.py

medium Unconstrained URL/host parameter "url" on "deep_analyze"MTC-CAP-007

Tool "deep_analyze" takes a URL/host parameter "url" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).