Back to skill

Security audit

Alibaba Cloud AI Video Emoji

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Alibaba Cloud emoji-video helper with disclosed provider use and bounded local output files.

Install only if you are comfortable using Alibaba Cloud Model Studio, providing a DASHSCOPE_API_KEY or Alibaba Cloud credential, and submitting public portrait image URLs for face-based video generation. Keep outputs in the documented output/aliyun-emoji/ directory and avoid using private or sensitive face images unless you have consent and understand the provider's data handling.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
91% confidence
Finding

The skill advertises operational behavior that involves both filesystem writes and network use, but it does not declare any tool scope such as permissions or allowed-tools. That creates an authorization gap where an agent may invoke broader capabilities than reviewers or policy layers expect, increasing the risk of unintended outbound requests or file modification during execution.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 14)May include surrounding context.

Validation

bash
mkdir -p output/aliyun-emoji
python -m py_compile skills/ai/video/aliyun-emoji/scripts/prepare_emoji_request.py && echo "py_compile_ok" > output/aliyun-emoji/validate.txt

Static analysis

No suspicious patterns detected.