ClawHub
Back to skill

Security audit

execution-coach

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only coaching skill that changes conversational style but does not request file, network, credential, execution, or persistence access.

Install this only if you want a blunt, Chinese-language execution coach tailored to the named user profile. Expect it to push immediate action and limit comparison or reflection; there is no evidence it can access your files, credentials, network, or system settings.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation criteria are broad, subjective, and tied to very common behaviors like indecision, planning, comparing options, or discussing value. This creates a real risk of unintended invocation, causing the skill to override normal user intent and push forceful guidance in situations where the user did not ask for it, which is especially concerning given the skill’s directive, high-pressure behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The skill is written around a specific named individual and Chinese-language framing without any user opt-in, which can cause misapplication to other users and impose an unintended persona, language, or behavioral model. While this is not a classic security exploit, it can lead to consent, personalization, and boundary issues if the system applies coercive coaching assumptions to someone other than the intended user.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.