Back to skill

Security audit

学程智伴

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Chinese academic companion skill with study, career, focus, and emotional-support features, but users should treat its mental-health support as non-professional guidance.

Install only if you want a Chinese-language academic and focus companion. Do not rely on it as a therapist or emergency service; for self-harm, suicidal thoughts, severe anxiety, or sustained depression, contact local emergency services, a crisis hotline, campus counseling, or a trusted person immediately. If your agent has persistent memory enabled, avoid sharing academic or emotional details you do not want remembered.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (9)

Vague Triggers

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The psychological-support triggers include broad phrases such as feeling anxious, tired, sad, pressured, or like a failure, which are common expressions and can map to sensitive mental-health flows without sufficient precision. In this context, false activation is more dangerous because the skill discusses crisis recognition and escalation, so misclassification could produce inappropriate mental-health guidance, miss genuine emergencies, or encourage unsafe reliance on the agent instead of professional help.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest is entirely written in Chinese and the example interactions assume Chinese-only use, while no opt-in, multilingual option, or justified region-specific limitation is stated. This can violate language/locale policy requirements when a skill constrains users to a specific language without explicit user choice.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly prioritizes natural-language, scene-triggered activation with automatic intent recognition, but it does not define clear activation boundaries, confirmation steps, or disambiguation rules. In a companion skill handling planning and psychological support, this can cause unintended mode switches, over-collection of sensitive context, or inappropriate responses triggered by ordinary conversation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

Several trigger phrases in this section are generic everyday expressions, increasing the chance that normal conversation will accidentally invoke planning, support, or decision workflows. This is risky because the assistant may respond as though a structured support function was requested when the user was only making a casual remark, leading to privacy issues, confusion, or unsafe overreach.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The persona is written entirely in Chinese and strongly constrains tone and interaction style without offering any language choice or fallback. This can exclude or confuse users who do not read Chinese, increase the risk of miscommunication in important guidance, and reduce informed user control over how they interact with the assistant.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill offers心理支持 and crisis-adjacent guidance, but the limitation that it is not a substitute for professional care is not made prominent near the beginning of the skill. In a mental-health context, delayed or weak safety framing can cause users to over-rely on the assistant during serious distress, including situations involving self-harm or severe anxiety/depression.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code file contains user-facing natural-language strings, docstrings, and CLI help text exclusively in Chinese, which effectively forces a specific language for interaction. The file does not indicate that Chinese is optional, user-selectable, or justified as a region-specific constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The module docstring presents the skill exclusively in Chinese, and the rest of the user-facing strings in the file follow the same pattern. Because there is no opt-in, language selection, or documented region-specific justification, this creates a natural-language locale policy concern under the language-choice rule.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The '说话风格' section instructs the skill to use Chinese-specific phrasing such as '用"咱们"拉近距离' and the entire skill is framed in Chinese, but it does not indicate that users may choose another language. This is a language/locale constraint expressed in natural language without opt-in.

Content

No source excerpt is available for this finding.