ClawHub
Back to skill

Security audit

Fact Check

Security checks for vulnerabilities and agentic risk

Overview

This fact-checking skill is a plain Markdown workflow for verifying claims and does not add code, persistence, or privileged access.

Before installing, understand that this skill may activate for broad verification-style requests and may lead the agent to perform web or source research. Use it for concrete factual claims, and treat specialist areas such as legal, medical, financial, or safety-critical questions as requiring domain-specific care beyond generic fact-checking.

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 (1)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill description is triggered by very broad phrases like 'verify,' 'confirm,' 'validate,' and 'check the accuracy,' which can overlap with many ordinary user requests outside a narrowly scoped fact-checking context. This can cause over-invocation, route sensitive or specialized requests into a generic verification workflow, and increase the chance the agent performs unintended web lookups or presents weakly grounded conclusions as authoritative.

Static analysis

No suspicious patterns detected.