Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
Without declared permissions the skill's intent is opaque and cannot be validated.
- Content
Security audit
Video Editor - 视频剪辑
Security checks for vulnerabilities and agentic risk
Overview
This is a coherent local video-editing skill, with ordinary file-output risks but no evidence of hidden network access, persistence, credential access, or malicious behavior.
Install only if you want a local Chinese-language video-editing helper. Check output filenames before running commands, especially merge, audio extraction, talk-video generation, or any command where you provide an explicit output path, because existing files may be overwritten.
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
- 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 (4)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The trigger list includes broad phrases such as '加文字', '变速', and '视频处理', which can match many ordinary user requests and cause the skill to activate unexpectedly. Unintended invocation is risky because this skill performs local media transformations that could overwrite files, consume resources, or act on the wrong content if selected automatically.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The skill describes commands that trim, merge, resize, replace audio, and otherwise transform media, but it does not warn about overwriting existing files, destructive edits, or the need to use separate output paths and backups. In a local file-processing skill, missing safety guidance increases the chance of accidental data loss or user confusion, especially when users may assume in-place edits are safe or reversible.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
This code file contains user-facing natural-language descriptions and CLI output exclusively in Chinese, including the module docstring and command descriptions. Because it forces a specific language for interaction without any user opt-in or documented locale constraint, it violates the language/locale policy criterion.
- Content