The Agent Skills Directory

[PROMPT_INJECTION]: No instructions found that attempt to override safety filters, bypass constraints, or extract system prompts. The instructions are strictly focused on creative writing and content optimization for the WeChat platform.
[DATA_EXFILTRATION]: No network operations, API calls, or attempts to access sensitive file paths (e.g., .ssh, .aws, .env) were identified. The skill operates entirely within the context of text generation.
[CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or passwords were found in the skill metadata or body.
[OBFUSCATION]: The content is clear and uses standard Markdown. There is no evidence of Base64 encoding, zero-width characters, homoglyphs, or other techniques to hide malicious intent.
[REMOTE_CODE_EXECUTION]: The skill does not perform any external downloads or execute remote scripts. It contains no commands like curl | bash or package installations.
[DYNAMIC_CONTEXT_INJECTION]: The skill does not use the !command syntax to execute shell commands at load time.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user-provided themes and topics (ingestion points), it lacks dangerous capabilities like file writing or command execution. The surface for exploitation is minimal and restricted to generating article content.

wechat-mp