ClawHub
Back to skill

Security audit

Fact-Checking Explainers

Security checks for vulnerabilities and agentic risk

Overview

This skill is a strict fact-checking workflow for explainers and does not contain code, persistence, credential handling, or hidden execution behavior.

Install this if you want a strict explainer fact-checking gate. Expect it to slow or block delivery until factual claims are supported, corrected, or removed; review its implicit invocation setting if you only want it used on explicit request.

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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill enables implicit invocation while its activation scope is broad and loosely defined around generic fact-checking and source verification tasks. This can cause the agent to invoke the skill unexpectedly in contexts containing sensitive, adversarial, or malformed inputs, expanding the attack surface for prompt injection or unsafe tool chaining even though the file itself contains no direct malicious logic.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.