Back to skill

Security audit

撒打算

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to be placeholder text with no functional instructions, code, data access, persistence, or malicious behavior.

This skill is low security risk based on the inspected files, but it also appears unfinished or non-useful. Install only if you intentionally want a placeholder skill; otherwise ask the publisher for a clear purpose, activation criteria, and operating boundaries.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill metadata and body provide no meaningful purpose, scope, or activation boundaries, making it difficult for a host agent or reviewer to determine when the skill should be invoked or what behavior is intended. Ambiguous skills increase the risk of accidental triggering, unsafe composition with other skills, and hiding malicious or policy-violating behavior inside otherwise unreviewable content.

Content

No source excerpt is available for this finding.