Back to skill

Security audit

Content Rewriter 内容多平台改写

Security checks for vulnerabilities and agentic risk

Overview

This is a simple writing skill for adapting user-provided content to Chinese social platforms and it does not request sensitive access or run code.

Install only if you want a Chinese social-media repurposing workflow. For generic rewriting, be aware that the broad activation wording may make this skill apply when you did not intend platform-specific output.

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
  • 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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description fixes the skill's behavior to Chinese social media platforms and the rest of the document prescribes platform-specific Chinese output styles without stating that users may choose another language or locale. This is a natural-language locale constraint and no opt-in or explicit justification is provided in the file.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation terms are broad and include common words like 'rewrite' and '转载', which can cause the skill to trigger during ordinary writing assistance requests rather than only when the user explicitly wants this specialized workflow. That creates scope overreach and unintended invocation risk, especially in agent environments where skills may auto-activate based on keyword matching.

Content

No source excerpt is available for this finding.