Back to skill

Security audit

video-watermark-anti-theft

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill about video watermarking and ownership proof, with no hidden code execution, persistence, or data exfiltration behavior found.

Review the broad activation terms and the unusual license split before installing. The skill appears safe from a security perspective, but it may trigger on general video or watermark questions and its documentation is not actually covered by the MIT license despite the package metadata saying MIT.

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 (4)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 94)May include surrounding context.

md
| 文档与理论文本 | 本 `SKILL.md`、`README.md`、其中「理论依据」段与一切理论表述 | **不在 MIT 覆盖范围内**:保留所有权利(All rights reserved) |

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger keywords are extremely generic ('video', 'anti', 'theft') and can cause the skill to activate in many unrelated conversations. Overbroad activation increases the chance of unintended routing, context hijacking, or the injection of irrelevant policy/content into sessions where the user did not request this skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest embeds a long trigger list with broad generic terms such as 'watermark', '加水印', and '版权保护' that can match common user requests outside the narrowly intended anti-theft context. This can cause the skill to be invoked unexpectedly, increasing prompt-surface exposure and the chance that unrelated conversations are routed into this skill's instructions or outputs.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The file begins with a Chinese-only scope notice while the rest of the license text is in English, creating a language-specific policy issue in natural-language content. There is no indication that the Chinese wording is optional, translated elsewhere, or required for a region-specific purpose.

Content

No source excerpt is available for this finding.