Security audit

双脑调度核心

Security checks for vulnerabilities and agentic risk

Overview

This skill is not executable malware, but it asks for broad control over task routing, context sharing, and final response format.

Use Review before installing. This skill is appropriate only if you intentionally want a central multi-skill orchestration workflow and your host enforces higher-priority instructions, user-requested output formats, and per-skill data minimization. Avoid using it where sensitive session context could be forwarded to unrelated downstream skills.

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

Findings (1)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:3
Finding: Skill Claims Exclusive Control Over Agent Dispatch and Output
Content: View full analysis
Remediation: View remediation

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 (2)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill declares very broad activation triggers such as any complex task, multi-skill coordination, dual-brain decision making, or generic orchestration keywords. Because this skill is the 'unique scheduling and decision center,' ambiguous invocation can cause over-triggering, route tasks into an over-privileged orchestrator unnecessarily, and expand the blast radius of prompt injection or logic-manipulation attacks across downstream skills.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The natural-language description and role instructions are written entirely in Chinese and present the skill's behavior in that language, with no indication that users may choose another language. Under the policy, language-specific behavior should be optional or explicitly justified as region-specific.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.