Back to skill

Security audit

早播新闻

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Zao Live audio-share link generator with broad trigger phrases that users should be aware of, but no hidden code, persistence, credential use, or local data access was found.

Install this only if you want generic Chinese news, podcast, or audio requests to potentially return a Zao Live share link. The publisher should narrow the trigger phrases or require clarification for ambiguous requests, but the inspected artifact does not show malicious behavior.

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 (2)

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill advertises broad natural-language triggers like '听新闻' and similar generic audio/news requests, which can cause the skill to activate when a user did not specifically intend to invoke this domain. That can route unrelated requests to an external service and produce unexpected link-sharing behavior, reducing user control and creating an invocation-hijacking risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The recommendation-style triggers are vague and unconstrained, making it unclear when this skill should be selected over other content or assistant capabilities. In practice, this increases the chance of accidental activation and inappropriate redirection to a third-party link instead of fulfilling the user's actual request.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.