ClawHub
Back to skill

Security audit

Alibaba Cloud AI Video Retalk

Security checks for vulnerabilities and agentic risk

Overview

The skill is a straightforward Alibaba Cloud VideoRetalk helper with disclosed local output files and expected provider API use.

Before using this skill, be comfortable sending public media URLs to Alibaba Cloud DashScope and storing the exact video/audio URLs locally under output/aliyun-videoretalk. Use a scoped DashScope API key where possible and clean the output directory if the media links are sensitive.

A.I.G

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

SkillSpector

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
92% confidence
Finding

The skill documents file-writing behavior (output/aliyun-videoretalk/...) but does not declare any corresponding tool scope such as permissions or allowed-tools. This creates a capability/transparency gap: a host may permit the skill to write files without explicit least-privilege declaration or user awareness, which can enable unintended persistence or artifact tampering.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
81% confidence
Finding

The validation step intentionally creates and writes files under output/aliyun-videoretalk/, which is a form of session persistence. While the writes are limited to expected build/output artifacts and not obviously malicious, persisted files can still leak request details, URLs, or other operational data across runs if the environment is shared or not cleaned up.

Content

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

Validation

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

Static analysis

No suspicious patterns detected.