Back to skill

Security audit

Content Adapter

Security checks for vulnerabilities and agentic risk

Overview

The scanners classify this skill as benign, with no malicious findings reported and two language-policy findings considered consistent with its purpose; confidence is medium because analysis was partial.

The verdict is benign, but benign does not mean risk-free. Consider whether the reported English-language restrictions suit your needs. Analysis covered all eight listed components but was marked partial because three local references could not be resolved, so the evidence is incomplete.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

The channel specification mandates English and prohibits Chinese without offering a language choice.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

Line 23 requires English-oriented writing, and line 38 explicitly prohibits Chinese. Although the audience is described as overseas engineers, that audience is not necessarily English-speaking, so the description does not establish a specific justification for the blanket language restriction.

Content

No source excerpt is available for this finding.

The content specification defaults to English without user opt-in.

Low
Category
Output Handling
Confidence
96% confidence
Finding

“英文为主” instructs the agent to produce primarily English content. The file neither offers a language choice nor explains a regional or other requirement that justifies this constraint.

Content

No source excerpt is available for this finding.