Security audit

詹明明·重讲一个概念

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese content-workflow skill for drafting concept videos; it reads and updates a content vault but shows no hidden code, network access, credential use, or destructive behavior.

Install this only if you want the zmm Chinese concept-script workflow operating on your content vault. Review proposed changes before allowing updates to drafts, rule files, published-content indexes, or calendar/frontmatter records, and be aware that broad concept-explanation prompts may invoke this specialized style.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The trigger phrases are broad natural-language requests like 'explain X properly' and 'why does more X lead to less Y', which can match ordinary user requests that are not clearly intended to invoke this skill. That creates overbroad activation risk: the skill may intercept general explanatory tasks and impose its own workflow, file-reading behavior, and output constraints without explicit user intent.

Natural-Language Policy Violations

Medium

Confidence: 84% confidence
Finding: The skill hard-codes a specific stylistic regime for outputs, including '零术语' and a prescribed persona/voice check, without indicating user consent or fallback behavior. If auto-invoked, this can override user preferences and distort neutral assistance into a mandated house style, which is a prompt-scope and user-intent violation rather than a memory-safety issue.

Natural-Language Policy Violations

Medium

Confidence: 91% confidence
Finding: The entire skill file is written as Chinese-only operational guidance and does not indicate any option for another language or user-selected locale. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified.

Static analysis

No suspicious patterns detected.