Back to skill

Security audit

pikpak-save

Security checks for vulnerabilities and agentic risk

Overview

The skill provides a controlled PikPak saving workflow with openly documented playback and download steps and no hidden automation.

Use a trusted PikPak CLI installation and confirm the account, selected files, and destination before each operation. Downloads can consume quota and overwrite local files. The referral code is optional. Live account and service behavior were not verified.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared purpose covers saving links into PikPak and checking task receipts. The supplied commands instead operate on file IDs to play content and write a file locally. These are distinct, undeclared capabilities rather than supporting details of link submission or task verification.

Content

No source excerpt is available for this finding.