x-reply
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's instructions are purely focused on linguistic style, character limits, and tone adjustment for social media interactions.
- [SAFE]: No external network requests, data exfiltration patterns, or sensitive file access were detected.
- [SAFE]: The binary .skill file is a standard ZIP archive containing the plain-text markdown source files (README.md, SKILL.md, etc.) for packaging purposes.
- [SAFE]: While the skill processes untrusted user input (replies from X), it lacks the capabilities (such as code execution or network access) that would make indirect prompt injection a significant risk.
Audit Metadata