Back to skill

Security audit

linkdigest-xiaohongshu-douyin-reader

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed LinkDigest API wrapper for reading public social-post links, with no evidence of hidden persistence, local data harvesting, or destructive behavior.

Install only if you are comfortable sending the link or copied share text to LinkDigest and using a LinkDigest API key. Avoid submitting private or sensitive links because the skill discloses that text results are cached per link and may be served again to others who ask for the same public link. Expect possible reliability issues because the bundled script references output/error helper functions that are not defined in the inspected file.

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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill requires environment access, network access, and shell execution but does not declare any explicit tool scope such as permissions or allowed-tools. That creates an over-privileged integration surface where a hosting agent may grant broader capabilities than necessary, making misuse of the API key or unintended outbound requests harder to constrain or audit.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest frames the skill as reading Xiaohongshu/RedNote or Douyin links, but the argparse description and help text state it reads Xiaohongshu, Douyin, TikTok, YouTube, X, and WeChat article links. This broadens the apparent behavior beyond the skill's declared scope, even though all traffic still goes to the same LinkDigest API.

Content

No source excerpt is available for this finding.