Back to skill

Security audit

南山没有海·个人成长技能包

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Chinese personal-growth advice skill with no code execution, persistence, credential access, or hidden data flows.

Install only if you want a Chinese-language mentor/persona style for personal-growth prompts. Do not rely on it for medical, mental-health crisis, legal, financial, or other professional advice, and be aware that the package publicly includes a phone number for contact.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill claims applicability to 'any growth problem,' creating an overly broad invocation scope that can cause the agent to respond in domains beyond its safe competence, including mental health, business, or interpersonal advice. Broad triggering increases the chance of inappropriate activation and low-quality or unsafe guidance in sensitive contexts.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill documentation publicly exposes a personal phone number in both the metadata and body, which creates unnecessary privacy and social-engineering risk unrelated to the core function of answering growth questions. Even if intentionally provided for business contact, embedding personal contact details in distributable skill content can enable scraping, spam, harassment, or unwanted direct outreach.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The instruction mandates a particular response style and language convention ('现代口语为主') without indicating that the user can choose another language or locale. This can violate language/locale policy expectations when no opt-in or alternative is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

This markdown file presents all persona guidance in Chinese and does not indicate that the user can choose another language. Under the language/locale policy rule, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.