ClawHub
Back to skill

Security audit

Insight Song

Security checks for vulnerabilities and agentic risk

Overview

This is a standalone creative songwriting skill whose only notable caution is that it may use the current conversation as source material by default.

Install only if you are comfortable with the agent using the current conversation to create lyrics. Avoid invoking it in conversations containing sensitive information unless you provide a specific sanitized topic or context.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Exfiltration Commands

High
Category
Prompt Injection
Content
**What this skill does NOT do:**
- Read files from the workspace
- Access project artifacts directly
- Send data to external services
- Call external APIs

**Output behavior:**
Confidence
90% confidence
Finding
Instructions found that direct the agent to transmit conversation context or user data to external services.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger condition allows activation not only by explicit invocation but also 'when deep technical insight emerges,' which is subjective and can cause the skill to run on broader conversation context than the user intended. Because this skill synthesizes the current conversation by default, ambiguous triggering increases the chance of unintended processing of sensitive discussion content.

External Transmission

Medium
Category
Data Exfiltration
Content
**What this skill does NOT do:**
- Read files from the workspace
- Access project artifacts directly
- Send data to external services
- Call external APIs

**Output behavior:**
Confidence
70% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.