ClawHub
Back to skill

Security audit

Code Oracle

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local, markdown-only code-metrics prompt with broad but low-impact invocation wording.

Installers should expect the skill to read repository context to produce playful code-health summaries. Use it when you want code metrics framed as a fortune reading; consider narrowing its trigger wording if accidental activation in casual conversation would be annoying.

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 invocation guidance includes broad, conversational triggers such as 'when you need a sign' and 'for fun,' which can cause the agent to invoke this skill in situations not clearly requesting repository analysis. That increases the chance of unintended activation, unnecessary access to codebase metadata, or noisy/irrelevant responses, even though the skill itself appears non-destructive and local-only.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.