tai-chi
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified in the analyzed files.
- [PROMPT_INJECTION]: The skill defines a specific roleplay persona for providing workplace communication strategies. It does not contain instructions to bypass AI safety guidelines, ignore system prompts, or extract sensitive model information.
- [DATA_EXFILTRATION]: There are no commands or functions that attempt to access local files, environment variables, or credentials. No network operations (such as curl or wget) are present.
- [REMOTE_CODE_EXECUTION]: The skill does not download external scripts or packages. It relies entirely on static markdown content.
- [COMMAND_EXECUTION]: No shell commands, subprocess calls, or privilege escalation attempts were found.
- [OBFUSCATION]: The content is written in clear text without any encoding (Base64, hex), hidden characters, or homoglyph substitutions.
Audit Metadata