Security audit

AI心理疗愈专家

Security checks for vulnerabilities and agentic risk

Overview

This is a document-only Chinese emotional-support skill with disclosed safety boundaries and no evidence of code execution, data access, network use, or persistence.

Install this only if you want a Chinese-language reflective emotional-support assistant. It should not replace professional mental-health care, and users should seek local emergency or clinical support for self-harm, suicide, violence, psychosis, or acute crisis situations.

A.I.G

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

SkillSpector

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 (6)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest description and core instructions are written entirely in Chinese and present the assistant persona and interaction style as Chinese by default, without offering a language choice or stating that the skill is limited to Chinese-speaking users. This can violate language/locale policy because it imposes a specific language experience absent explicit user opt-in or a justified regional scope.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger phrases are broad, common expressions about mood, uncertainty, and life meaning, so the skill may activate during ordinary conversation without the user clearly intending to invoke a mental-health-oriented workflow. In this context, unintended activation is more sensitive than usual because the skill deals with emotional vulnerability, existential distress, and career/life decisions, which can steer users into quasi-therapeutic interactions they did not explicitly request.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 80% confidence
Finding: The user-facing display name, description, tags, and author metadata are entirely in Chinese, which indicates a fixed language presentation with no stated language-choice or opt-in mechanism. Under the policy, forcing a specific language without offering user choice can be a natural-language policy violation unless clearly justified as region-specific.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This file contains all user-facing guidance in Chinese and does not indicate that language selection is optional or configurable. Under the policy rule for natural-language violations, forcing a specific language without user opt-in is a locale/language policy issue.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: Natural-language fields including display name, description, triggers, tags, license, and security notes are presented exclusively in Chinese. If this skill is intended for a general audience, this effectively forces a specific language without indicating user opt-in or documenting a justified locale restriction.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: This manifest describes the skill as suitable for wide-ranging situations such as emotional distress, relationships, dreams, meaning, and life transitions, but it does not define specific activation phrases, boundaries, or exclusion examples. In a manifest file, such broad invocation scope can make it unclear when the skill should activate versus when a general conversation skill should respond.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.