ClawHub
Back to skill

Security audit

Analyze

Security checks for vulnerabilities and agentic risk

Overview

This is a simple analysis-guidance skill with broad scope, but it does not request dangerous access, run code, or hide behavior.

Install only if you want a general analysis-formatting aid. For legal, medical, security, financial, or other high-impact decisions, treat its output as a thinking aid and use appropriate expert review.

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 description is extremely broad ('Structured analysis for any input. Data, code, text, decisions, visuals.'), which can cause it to activate in many unrelated contexts and process sensitive or safety-critical material without domain-specific guardrails. Overbroad activation increases the chance of misuse, prompt collisions, and unsafe reliance because the skill presents itself as generally applicable while lacking constraints on scope, expertise, or exclusion criteria.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.