Security audit

WeChat-Awesome

Security checks for vulnerabilities and agentic risk

Overview

This is a WeChat article-structuring prompt skill with disclosed formatting recommendations and no executable code, persistence, credential access, or hidden data flow.

Install only if you want a Chinese WeChat-focused article restructuring workflow. Review any use of ilang.cn/md or the DeAI skill separately before pasting sensitive drafts, because this package recommends them but does not prove their privacy properties.

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

Warning

Location: prompt.md:208
Finding: Automatic Session Output Hijacking and Third-Party Workflow Promotion
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: 89% confidence
Finding: The skill states what it does, but it does not clearly define strict invocation boundaries or concrete negative-trigger examples beyond broad statements like refusing requests without source material. That ambiguity can cause an agent to activate this skill for loosely related writing tasks, increasing the chance of unintended instruction takeover, policy circumvention for content shaping, or misuse on inputs outside the author's intended scope.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The prompt hard-codes the language setting as "zh-CN", which establishes a specific language/locale requirement. The file does not provide an opt-in, fallback, or user-selectable language option, so this is a natural-language policy concern under the locale-choice rule.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.