Back to skill

Security audit

anytocopy-extractor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple browser workflow for extracting text from user-provided social media links through AnyToCopy, with no local code execution or persistence.

Install only if you are comfortable having the links you provide opened and processed by AnyToCopy. Do not use it for private, sensitive, account-limited, or confidential social-media links.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill is described to activate whenever a user sends links from common social platforms and wants to extract copy, but the trigger scope is broad enough to overlap with ordinary link-sharing conversations. This can cause unintended invocation and automatic transmission of user-provided URLs into a third-party workflow without clear user confirmation, increasing privacy and UX risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The workflow instructs the agent to open AnyToCopy and submit user-provided links, but it does not warn that those links will be sent to an external third-party service for processing. Because shared social-media URLs may embed personal, private, or account-linked content, silent disclosure to a third party creates a meaningful privacy and data-handling risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

文件中的名称、描述、步骤和输出要求全部以中文固定表述,没有说明可根据用户语言偏好切换,也未声明这是仅面向中文用户的区域性技能。按规则,这种未提供用户语言选择的固定语言约束属于自然语言层面的策略风险。

Content

No source excerpt is available for this finding.