Security audit

Content System Wechat Formatter

Security checks for vulnerabilities and agentic risk

Overview

This WeChat HTML formatter has a coherent purpose, but its runtime imports executable code from a hard-coded personal folder outside the reviewed package.

Review this skill before installing. It appears intended for legitimate WeChat article formatting, but the runtime should be changed to package or pin the renderer instead of loading it from /Users/Abigale/.codex/skills/wechat-article-workflow/scripts. Also confirm generated output filenames to avoid overwriting existing ready HTML files.

A.I.G

Vulnerability Patterns

Tool Hijacking and SpoofingModifies or replaces tools so legitimate-looking calls execute attacker logic
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

Findings (1)

T07 · Tool Hijacking and Spoofing

Error

Location: runtime.py:9
Finding: Hard-Coded External Module Path Enables Python Import Hijacking
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)

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The manifest description says to use the skill when Codex needs 公众号排版预览, which imposes a Chinese-language/localized framing in the activation description. The file does not offer any user language choice or explicitly justify this locale-specific wording as a documented regional constraint.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This markdown file documents a file-writing behavior by specifying that the skill will write output to content-production/ready/<slug>-wechat.html. Under the markdown-specific warning rule, behaviors that affect user data or the filesystem should be disclosed with a clear warning, but the description provides no caution about overwriting existing files or creating artifacts in the workspace.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.