Back to skill

Security audit

Stress Manager

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only stress-coping skill with disclosed limits and no code execution, data access, persistence, or credential use.

Before installing, note that the skill is mainly written for Chinese-language stress-support use and includes China-specific examples. Users outside that locale should ask for local resources instead, and anyone in crisis or at risk of self-harm should use local emergency or licensed professional support rather than relying on this skill.

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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown file presents the skill's purpose, examples, and responses only in Chinese, which can amount to forcing a specific language on users without opt-in. The policy allows locale constraints only when they are explicitly justified or when users are offered a language choice, neither of which appears here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill recommends Chinese-language and China-specific resources and financial products without checking the user's language, region, or eligibility. This can misdirect vulnerable users to unusable or inappropriate support, and in a mental-wellness context that reduces access to timely, relevant help when the user may already be distressed.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The listed triggers include generic phrases such as "事情太多了", "我最近特别累", "I feel overwhelmed", and "too much pressure", which can appear in ordinary conversation outside the intended stress-support context. The file does not provide exclusion conditions or negative examples to clarify when the skill should not activate, increasing the risk of unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.