Back to skill

Security audit

深度写作

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese deep-writing workflow skill with no executable code, persistence, credential access, or hidden data movement.

Install this if you want a staged Chinese writing assistant for briefs, outlines, and long-form drafts. Be aware that its default outputs and continuation prompts are in Chinese; ask the agent for another language if needed.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file states "Default language: Chinese," which imposes a locale/language default as part of the skill's operating contract. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the skill offers choice or clearly justifies a region-specific constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The manifest presents the skill as Chinese-language oriented via the display name and description, and the default prompt explicitly instructs creation of 'deep Chinese content'. This imposes a locale/language constraint without any visible opt-in, alternative language option, or documented regional justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The template content and the required continuation input are entirely in Chinese, including the instruction to enter “继续” to proceed. This imposes a specific language/locale on users without offering an opt-in or documenting a justified region-specific constraint, which matches the language-policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Line L222 instructs the skill to prefer precise, readable Chinese, which imposes a language preference as a default behavior. Because the document does not present this as optional or limited to a clearly documented China-specific use case, it creates a natural-language policy concern around forced locale/language selection.

Content

No source excerpt is available for this finding.