Back to skill

Security audit

Cca Domain4

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language CCA study skill that teaches prompt engineering and structured output without hidden execution, persistence, or data collection.

Install this if you want a Chinese CCA domain 4 study tutor. Be aware it may activate on broad prompt-engineering requests and it declares broad coding tools, though the inspected instructions do not use them automatically or ask for sensitive data.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger phrase "提示工程" is broad enough to match many normal user requests about prompt engineering, causing this skill to activate outside its narrow intended CCA tutoring context. That can route conversations to an unrelated skill unexpectedly, degrading behavior and potentially exposing tool-enabled capabilities in situations where they are not needed.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill content and description are written to drive Chinese-language tutoring without any indication that language should follow user preference. If invoked for a non-Chinese-speaking user, it can force an unexpected language switch, impair comprehension, and increase the chance that safety-relevant guidance is misunderstood.

Content

No source excerpt is available for this finding.