trainer-write-wechat-article
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Prompt Injection] (SAFE): The skill contains only writing guidelines and does not include any instructions designed to subvert the agent's core instructions or safety filters.
- [Data Exposure & Exfiltration] (SAFE): No access to system files, hardcoded credentials, or external network requests were detected.
- [Obfuscation] (SAFE): All content is in plain-text Markdown without any encoded or hidden strings.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): No external scripts, package managers, or remote execution patterns are present in the skill.
- [Indirect Prompt Injection] (LOW): While the skill is intended to process user-provided topics, it lacks any 'write' or 'execute' capabilities that could be exploited if malicious content were provided in the input; it only generates text based on the provided framework.
Audit Metadata