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
Bytesagain Video Script Creator
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local video-script template generator with no evidence of hidden data access, persistence, exfiltration, or destructive behavior.
Reasonable to install if you want a simple local video-script generator. Be aware that Douyin and Bilibili outputs are Chinese-oriented, and some commands may need bug fixes before they run reliably; no sensitive data access or background behavior was found.
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
- 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
Findings (6)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The Douyin command emits only Simplified Chinese script text and labels, which imposes a specific language/locale in natural-language output. The file does not provide an opt-in, fallback, or explicit justification that this locale restriction is required.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
The Bilibili command generates natural-language script content entirely in Chinese, but the skill does not indicate that this is an intentional region-specific mode or provide a language option. This can violate language/locale policy when users are not given a choice.
- Content
Vague Triggers
Low
- Category
- Not specified by scanner
- Confidence
- 85% confidence
- Finding
The manifest description says to use the skill when scripting tutorials, creating content, or planning videos across multiple platforms, which is broad and lacks clear boundaries on when the skill should or should not activate. Because it does not provide narrower trigger phrases, constraints, or exclusion examples, it may overlap with ordinary requests for general writing or planning help.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 77% confidence
- Finding
The command descriptions switch from English to Chinese for Douyin and Bilibili entries, but the document does not explain whether output language is chosen by the user or constrained by platform. This can create an implicit language expectation without documented opt-in or justification.
- Content
Vague Triggers
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The phrase 'Use when planning video content, need a script framework fast, want platform-optimized structure, or generating hook ideas for any topic' covers a wide range of common creative tasks without clear limits. This ambiguity increases the chance of unintended invocation for generic brainstorming or writing requests.
- Content
Static analysis
No suspicious patterns detected.