Back to skill

Security audit

Huo15 Todo

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed todo-planning workflow helper and does not request code execution, credentials, persistence, or privileged access.

Install this if you want the agent to use a structured checklist for multi-step tasks. Be aware that broad aliases may activate it during ordinary planning requests, and non-Chinese users may prefer a version that explicitly follows the user's language.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill is written entirely in Chinese and presents its operating rules, examples, and workflow in Chinese without any indication that language should follow user preference. If an agent applies these instructions verbatim in a different-language session, it can degrade usability, cause misunderstandings, and steer outputs into an unintended locale.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The alias list includes very broad trigger phrases such as '待办规划', '任务清单', 'todo mode', and 'task planning', which are common ways users describe ordinary work rather than a deliberate request for this specific skill. In systems that auto-select skills from natural-language matches, this can cause unintended activation, altering agent behavior and potentially overriding more appropriate instructions or workflows.

Content

No source excerpt is available for this finding.