ClawHub
Back to skill

Security audit

Apollo Mode

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, user-controlled workflow mode that stores only an on/off state and templates for coding-task planning.

Before installing, be aware that this skill can change how the agent handles coding tasks until disabled by writing an on/off state file. It does not request credentials, network access, shell execution, or broad file access, but the naming and language mix may make its commands less clear.

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)

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The manifest description is written only in Chinese, while the command triggers and examples are split across Russian and English. This introduces an implicit language/locale constraint without stating that users may interact in their preferred language or that the skill is region-specific.

Static analysis

No suspicious patterns detected.