ClawHub
Back to skill

Security audit

AI Researcher

Security checks for vulnerabilities and agentic risk

Overview

This is a simple research-prompt skill with no hidden code, persistence, credential handling, or destructive behavior.

Reasonable to install if you want a general research assistant. Because the skill is intentionally broad, users should give clear topic boundaries and source expectations when invoking it.

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
92% confidence
Finding

The manifest description says the skill performs deep research on "any topic" and provides summaries "on demand," but it does not define specific trigger phrases, scope boundaries, or exclusion conditions. In a markdown/manifest context, this broad phrasing increases the chance of unintended invocation for ordinary requests that mention research or summaries.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.