Back to skill

Security audit

doubao-copywriter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Doubao copywriting workflow, with the main caution that it may involve logging into Doubao through an agent-controlled browser.

Install this only if you are comfortable using Doubao for writing generation. When logging in, treat QR codes and account pages as sensitive, use the local-browser fallback if possible, and sign out of Doubao in the agent browser after use if the session should not remain active.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill’s trigger scope is very broad, covering generic writing tasks such as social posts, articles, and scripts without clear boundaries for when the skill should or should not be invoked. Overly broad invocation can cause the agent to route ordinary user requests into a workflow that unnecessarily opens an external website and requests login, increasing exposure to phishing-like flows, privacy risks, and unintended use of third-party services.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The workflow instructs the agent to click login and send a screenshot for QR-code scanning, but it does not warn that screenshots of login pages may expose QR codes, session state, account identifiers, or other sensitive authentication artifacts. In an agent context, facilitating login through shared screenshots can normalize unsafe authentication handling and could lead to account takeover or leakage of session-related information if the image is intercepted, retained, or mishandled.

Content

No source excerpt is available for this finding.