ClawHub
Back to skill

Security audit

Fact Cross Check

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward fact-checking helper that uses web search and web fetch, with no local persistence, credentials, or executable code.

Install this only if you are comfortable with verification queries being sent through OpenClaw's configured web search provider. Be aware that the broad multilingual trigger terms may cause it to activate for some general discovery requests, so review generated searches before sharing sensitive wording.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation language is broad enough to trigger on many ordinary information-seeking prompts, which can cause the skill to run outside narrowly intended verification scenarios. In a skill that influences search, source selection, and confidence judgments, over-triggering can increase the chance of unnecessary web access, prompt-scope expansion, or reliance on this skill when the user did not explicitly request cross-checking.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger list includes very broad terms such as 'verify', 'find and verify', and especially Chinese terms like '尋找' and '搵' that can match many ordinary user requests. This can cause unintended skill activation, routing benign queries through web-search behavior and sending user prompts to external search providers when the user did not explicitly intend to invoke this skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The manifest hard-codes trigger phrases in specific languages/scripts ('驗證, 查證, 核實, 尋找, 搵') but does not state that these are optional, user-configurable, or limited to a region-specific deployment. That can be a language/locale policy issue because the skill behavior is partially gated by fixed-language terms without user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.