Security audit

Publish Checklist

Security checks for vulnerabilities and agentic risk

Overview

This is a publishing checklist with no code execution or hidden access, though it does impose a broad workflow rule for public content.

Install this if you want a strict pre-publication checklist. Be aware it tells the agent to apply a mandatory bilingual convention for PRs/issues and to load the checklist before public-facing content, so it may affect workflow style even though it does not add technical access.

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
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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This markdown file contains a natural-language instruction that PRs and issues must be submitted bilingually in Chinese and English. That is a language policy constraint applied broadly to users, and the file does not offer a choice, opt-in, or documented justification for the requirement.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.