Security audit

Perfect Automation

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language workflow-planning guide for automation tools, with broad trigger wording but no hidden execution, credential access, or persistence in the skill itself.

Install only if you want Chinese-language help designing automation workflows. Review any generated workflows before activation, especially ones that post publicly, create invoices, update CRM records, or touch customer data; keep credentials out of generated JSON as the skill itself recommends.

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)

Vague Triggers

High

Confidence: 97% confidence
Finding: The trigger phrases in the metadata are broad everyday terms such as '自动化', '自动', and '提效', which can cause the skill to activate in many unrelated conversations. Overly broad invocation increases the chance of accidental routing to this skill, leading to inappropriate automation guidance being injected when the user did not intend to invoke it.

Vague Triggers

High

Confidence: 98% confidence
Finding: The standalone trigger list repeats highly ambiguous phrases like '自动', '工作流', and '提效' without contextual boundaries. This makes accidental invocation even more likely because these are common terms that could appear in many benign requests unrelated to automation tooling.

Natural-Language Policy Violations

Medium

Confidence: 90% confidence
Finding: The skill description and the rest of the document are presented in Chinese, but there is no statement that the user may choose another language or locale. This creates a language-policy concern because the skill appears to impose a specific language without opt-in or documented regional necessity.

Static analysis

No suspicious patterns detected.