ClawHub
Back to skill

Security audit

Claw Talk

Security checks for vulnerabilities and agentic risk

Overview

This is a simple conversation-coaching skill with no executable code, persistence, credential access, or hidden data behavior.

Installers should be aware that this skill may be invoked by broad speaking-related phrases, but its reviewed contents are limited to benign coaching templates and presentation guidance.

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
Confidence
94% confidence
Finding
The trigger list includes several broad, common phrases such as "voice chat," "talking points," "presentation script," and "public speaking," which can match many ordinary user requests outside the narrow intent of this specific skill. This can cause unintended invocation, leading to user confusion, misrouting to the wrong capability, or accidental exposure of skill-specific behavior when the user did not explicitly request it.

Static analysis

No suspicious patterns detected.