Security audit

Danny_Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language media publishing helper with no bundled code, persistence, credential access, or hidden behavior found.

Install only if you want a Chinese-language assistant for preparing short-video publishing materials. Review any generated titles, descriptions, covers, and videos before using them, and avoid providing private media unless you intend the agent to process it into derivative outputs.

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

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 (3)

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The skill describes combining images into videos and producing output files, but does not warn users that their media files may be processed and transformed. This lack of disclosure can lead to privacy and consent issues, especially if users do not realize local or sensitive media assets will be consumed to create derivative outputs.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger phrase "帮我发布到抖音和快手" is broad enough to overlap with ordinary user requests, making accidental or unintended invocation plausible. In a skill that can process media inputs and generate publishing-related outputs, ambiguous triggering increases the chance that user content is handled without clear intent or informed context switching.

Natural-Language Policy Violations

Low

Confidence: 88% confidence
Finding: The natural-language instructions, examples, and usage guidance are all in Chinese, which can amount to a forced language/locale assumption if users are not given an opt-in or alternative. The file does not state that the skill is intentionally limited to Chinese-speaking users or a China-specific operational context.

Static analysis

No suspicious patterns detected.