Skill: URLCheck : URL security scanner

Owner: cplusdev

Summary: Companion skill for @cybrlab/urlcheck-openclaw. Requires URLCheck plugin tools to assess URLs for threats and intent alignment before navigation.

Tags: URL:1.0.1, intent-aware:1.0.1, latest:1.0.4, link:1.0.1, mcp:1.0.1, openclaw:1.0.1, security:1.0.1, url-assessment:1.0.1

Version history:

v1.0.4 | 2026-02-17T22:11:48.301Z | user

• Added documentation for asynchronous URL scan workflows, including async scan initiation, task status, and result retrieval tools.
• Described usage and fields for new async endpoints: url_scanner_scan_async, url_scanner_scan_with_intent_async, url_scanner_tasks_get, url_scanner_tasks_result, etc.
• Updated field documentation to include intent_alignment, clarifying alignment values and their meanings.
• Expanded tool unavailability guidance to cover async/task APIs.

v1.0.3 | 2026-02-11T09:55:17.079Z | user

• Shortened the SKILL.md title to “Intent-aware URL security verifier for agents.”
• No changes to functionality; documentation language was made more concise.
• No changes detected in skill files or code.

v1.0.2 | 2026-02-09T15:49:16.813Z | user

• Added a "Quick Start" section with installation and usage instructions for users.
• Stated no API key is needed for trial mode (up to 100 requests/day); provided contact for higher limits.
• Introduced a "Tool Availability Fallback" section: if required tools are unavailable, advise the user to install the plugin and restart the gateway.
• No functional or interface changes to verification flow.

v1.0.1 | 2026-02-09T15:37:11.677Z | user

Clarified companion dependency: requires @cybrlab/urlcheck-openclaw plugin tools; improved user-ready usage guidance.

v1.0.0 | 2026-02-09T08:19:44.815Z | user

Initial ClawHub release of the URLCheck companion skill. Guides agents to run threat and intent-aware URL assessment before navigation and apply directive-based next-step decisions.

Archive index:

Archive v1.0.4: 2 files, 2772 bytes

Files: SKILL.md (5375b), _meta.json (127b)

File v1.0.4:SKILL.md

---

name: urlcheck description: Companion skill for @cybrlab/urlcheck-openclaw. Requires URLCheck plugin tools to assess URLs for threats and intent alignment before navigation. user-invocable: true metadata: {"openclaw":{"requires":{"config":["plugins.entries.urlcheck-openclaw.enabled"]}}}

URLCheck - Intent-aware URL security verifier for agents

You have access to a URL verification system that checks target web resources for security threats and evaluates whether they appear to correspond to the user's browsing goals. Use it to verify any URL before taking the next step — navigating, clicking, opening, or redirecting.

The goal is not only to detect threats but to help assess whether the target resource appears aligned with what the user actually intends to accomplish.

Quick Start (For Users)

1. Install plugin and restart gateway:

openclaw plugins install @cybrlab/urlcheck-openclaw
openclaw gateway restart

1. Verify plugin and skill:

openclaw plugins list | grep -i urlcheck
openclaw skills list | grep -i urlcheck

1. Try it:

Before opening https://example.com, run url_scanner_scan_with_intent with intent "log in to my account" and tell me whether I should proceed.

No API key is needed for trial mode (up to 100 requests/day). For higher limits, contact contact@cybrlab.ai.

When to Verify

Verify a URL before any of these actions:

• Opening a link the user provides or that you discover
• Navigating to a page on the user's behalf
• Following a redirect chain
• Downloading a file from a URL
• Submitting credentials to a login page
• Taking any action where the destination matters to the outcome

Do not verify URLs that are internal references (localhost, file://, or intranet addresses the user is already working with).

Which Tool to Use

url_scanner_scan — Threat-focused verification.

• Required parameter: url (the URL to verify).
• Use when the user has not stated a specific purpose. The system evaluates the URL for phishing, malware, and suspicious patterns.

url_scanner_scan_with_intent — Threat verification plus destination-intent alignment.

• Required parameter: url (the URL to verify).
• Optional parameter: intent (the user's stated purpose).
• Use when the user has mentioned a purpose such as "log in", "purchase", "download", "book", or "sign up". Pass that purpose as the intent parameter so the system can evaluate whether the target resource appears to correspond to the user's goal, in addition to checking for threats.

Prefer url_scanner_scan_with_intent whenever intent is available. This catches mismatches that threat-only analysis may miss — for example, a legitimate site that may not be the one the user intended to use for their goal.

Async workflow tools (non-blocking)

• url_scanner_scan_async and url_scanner_scan_with_intent_async start scans and return a task handle immediately.
• url_scanner_tasks_get checks task status.
• url_scanner_tasks_result returns the completed scan payload.
• url_scanner_tasks_list lists current tasks.
• url_scanner_tasks_cancel cancels a queued or running task.

Use async tools when you need non-blocking execution or explicit task lifecycle control. For normal conversational checks, direct tools are usually sufficient.

How to Act on Results

Every verification returns an agent_access_directive. Follow it:

• ALLOW — Proceed with navigation. Inform the user briefly that the URL was assessed. Do not guarantee safety.
• DENY — Do not navigate. Tell the user the URL was flagged and include the agent_access_reason. Suggest they verify the URL or use an alternative.
• RETRY_LATER — Verification could not complete (temporary issue). Wait a moment and retry once. If it fails again, inform the user.
• REQUIRE_CREDENTIALS — The target requires authentication. Ask the user how they would like to proceed before continuing.

Interpreting Additional Fields

• risk_score (0.0 to 1.0): threat probability. Lower is safer.
• confidence (0.0 to 1.0): how certain the analysis is.
• analysis_complete (true/false): whether the full analysis finished. If false, the result is based on partial analysis — note this to the user when relevant.
• intent_alignment: alignment signal between user purpose and observed destination behavior/content.
  • misaligned: evidence suggests mismatch with user intent.
  • no_mismatch_detected: no explicit mismatch signal detected.
  • inconclusive: insufficient evidence to verify alignment.
  • not_provided: no intent was provided.

Timing

Verifications typically take 30 to 90 seconds. Do not set short timeouts or abandon verification prematurely. Wait for the result before proceeding.

User-Facing Messaging

• Report the outcome clearly using agent_access_directive and agent_access_reason, and state whether the destination appears aligned with the user's goal when intent is provided.
• Use confidence-aware language based on scan evidence (for example, "appears low-risk based on this scan"); avoid absolute guarantees.

Tool Availability Fallback

If URLCheck tools are unavailable (including async/task variants), do not proceed with scan logic. Tell the user to install the plugin and restart the gateway.

File v1.0.4:_meta.json

{ "ownerId": "kn7eyydvg5d0y24rj0p8x6wws980tg0n", "slug": "urlcheck", "version": "1.0.4", "publishedAt": 1771366308301 }

Archive v1.0.3: 2 files, 2402 bytes

Files: SKILL.md (4495b), _meta.json (127b)

File v1.0.3:SKILL.md

---

name: urlcheck description: Companion skill for @cybrlab/urlcheck-openclaw. Requires URLCheck plugin tools to assess URLs for threats and intent alignment before navigation. user-invocable: true metadata: {"openclaw":{"requires":{"config":["plugins.entries.urlcheck-openclaw.enabled"]}}}

URLCheck - Intent-aware URL security verifier for agents

You have access to a URL verification system that checks target web resources for security threats and evaluates whether they appear to correspond to the user's browsing goals. Use it to verify any URL before taking the next step — navigating, clicking, opening, or redirecting.

The goal is not only to detect threats but to help assess whether the target resource appears aligned with what the user actually intends to accomplish.

Quick Start (For Users)

1. Install plugin and restart gateway:

openclaw plugins install @cybrlab/urlcheck-openclaw
openclaw gateway restart

1. Verify plugin and skill:

openclaw plugins list | grep -i urlcheck
openclaw skills list | grep -i urlcheck

1. Try it:

Before opening https://example.com, run url_scanner_scan_with_intent with intent "log in to my account" and tell me whether I should proceed.

No API key is needed for trial mode (up to 100 requests/day). For higher limits, contact contact@cybrlab.ai.

When to Verify

Verify a URL before any of these actions:

• Opening a link the user provides or that you discover
• Navigating to a page on the user's behalf
• Following a redirect chain
• Downloading a file from a URL
• Submitting credentials to a login page
• Taking any action where the destination matters to the outcome

Do not verify URLs that are internal references (localhost, file://, or intranet addresses the user is already working with).

Which Tool to Use

url_scanner_scan — Threat-focused verification.

• Required parameter: url (the URL to verify).
• Use when the user has not stated a specific purpose. The system evaluates the URL for phishing, malware, and suspicious patterns.

url_scanner_scan_with_intent — Threat verification plus destination-intent alignment.

• Required parameter: url (the URL to verify).
• Optional parameter: intent (the user's stated purpose).
• Use when the user has mentioned a purpose such as "log in", "purchase", "download", "book", or "sign up". Pass that purpose as the intent parameter so the system can evaluate whether the target resource appears to correspond to the user's goal, in addition to checking for threats.

Prefer url_scanner_scan_with_intent whenever intent is available. This catches mismatches that threat-only analysis may miss — for example, a legitimate site that may not be the one the user intended to use for their goal.

How to Act on Results

Every verification returns an agent_access_directive. Follow it:

• ALLOW — Proceed with navigation. Inform the user briefly that the URL was assessed. Do not guarantee safety.
• DENY — Do not navigate. Tell the user the URL was flagged and include the agent_access_reason. Suggest they verify the URL or use an alternative.
• RETRY_LATER — Verification could not complete (temporary issue). Wait a moment and retry once. If it fails again, inform the user.
• REQUIRE_CREDENTIALS — The target requires authentication. Ask the user how they would like to proceed before continuing.

Interpreting Additional Fields

• risk_score (0.0 to 1.0): threat probability. Lower is safer.
• confidence (0.0 to 1.0): how certain the analysis is.
• analysis_complete (true/false): whether the full analysis finished. If false, the result is based on partial analysis — note this to the user when relevant.

Timing

Verifications typically take 30 to 90 seconds. Do not set short timeouts or abandon verification prematurely. Wait for the result before proceeding.

User-Facing Messaging

• Report the outcome clearly using agent_access_directive and agent_access_reason, and state whether the destination appears aligned with the user's goal when intent is provided.
• Use confidence-aware language based on scan evidence (for example, "appears low-risk based on this scan"); avoid absolute guarantees.

Tool Availability Fallback

If url_scanner_scan or url_scanner_scan_with_intent is unavailable, do not proceed with scan logic. Tell the user to install the plugin and restart the gateway.

File v1.0.3:_meta.json

{ "ownerId": "kn7eyydvg5d0y24rj0p8x6wws980tg0n", "slug": "urlcheck", "version": "1.0.3", "publishedAt": 1770803717079 }