Back to skill

Security audit

健身房

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple nearby-gym lookup guide that requests location only for that purpose and does not include code, persistence, or privileged behavior.

Before installing, be aware that the skill depends on user-authorized location data and contains a reference to a local STANDARD_RESPONSE.md file that is not bundled, so response formatting may need clarification by the publisher.

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 (1)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The manifest description and trigger examples combine English and Chinese phrases, while the rest of the skill content is primarily Chinese. This may create a language/locale policy concern because the skill appears to assume bilingual handling without explicitly offering the user a language choice or documenting that the skill is intended for a Chinese-speaking context.

Content

No source excerpt is available for this finding.