x-mastery-mentor
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to provide writing and growth advice for X/Twitter. All instructions and reference materials are consistent with this purpose and leverage well-known industry frameworks.
- [SAFE]: Data persistence is handled locally within the
user-data/directory. This is used to store account diagnostics and personalized strategies for the user, which is a legitimate use of the agent's filesystem capabilities for a mentoring tool. - [SAFE]: External data fetching is performed using platform-provided browser tools (
computer-use,claude-in-chrome) to accessx.com. This is explicitly disclosed to the user and is necessary for the 'Account Diagnosis' feature. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes untrusted external content (user tweets from X.com) to generate reports. However, this is inherent to the tool's diagnostic function, and the skill contains no malicious intent or attempts to override system safety guidelines.
- [SAFE]: No obfuscation, hidden URLs, or malicious remote code execution patterns were detected across the skill's instructions or its extensive research library.
Audit Metadata