Back to skill

Security audit

jackyshen-gen-short-video-script

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown skill that helps generate short social-video scripts and does not request system access, credentials, persistence, or code execution.

Before installing, expect this skill to steer relevant requests toward structured short-form video scripts and mostly English templates; users wanting Chinese or another language should specify the target language and platform in the request.

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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description uses broad trigger phrases such as 'short video script' and generic platform-content requests, which can cause the skill to activate outside its intended scope. Over-broad activation increases the chance that unrelated user requests are routed into this skill, producing irrelevant or policy-misaligned outputs and making downstream behavior less predictable.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
77% confidence
Finding

The skill heavily anchors output format, hooks, CTAs, and examples in English without offering language selection or documenting a locale requirement, despite referencing Chinese and global platforms. This can lead to unintended language forcing, degraded user trust, and inappropriate outputs for users expecting localized content, especially when the orchestration system selects the skill for non-English contexts.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.