ClawHub
Back to skill

Security audit

Geo Fact Checker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward fact-checking helper that uses web research and optional claim extraction to verify and improve factual content.

Install this if you want an agent to fact-check factual drafts using web evidence. Be aware it may trigger on many content-review tasks with factual claims and may suggest rewritten wording; review citations and corrections before applying them to important legal, medical, financial, or public-facing content.

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 (2)

Vague Triggers

Medium
Confidence
96% confidence
Finding
This markdown file says to use the skill "aggressively whenever" the user mentions broad terms like fact-checking, verifying, or validating, and further says to prefer triggering it whenever there is any non-trivial factual content. Those conditions overlap with many ordinary writing and research requests, making the activation scope ambiguous and likely to cause unintended invocation.

Missing User Warnings

Low
Confidence
79% confidence
Finding
The module docstring states that the surrounding skill may 'apply corrections in the user's content,' which is a user-data-affecting action. In this file there is no confirmation flow, warning comment, or user-facing disclosure tied to that behavior, so the code documentation understates a potentially modifying operation.

Static analysis

No suspicious patterns detected.