yichen-x-slicer
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a secure content routing mechanism that strictly follows a same-author chain for threads and excludes external replies or quotes, minimizing exposure to untrusted content.\n- [SAFE]: Network operations are tightly controlled. The fetchAllowedBuffer and assertAllowedHttpsUrl functions restrict outbound requests to a whitelist of trusted domains (api.fxtwitter.com, pbs.twimg.com, video.twimg.com) and enforce HTTPS, preventing data exfiltration to unauthorized endpoints.\n- [SAFE]: The skill prevents path traversal attacks by using a safeOutputPath helper that validates every file operation (HTML generation, image downloads, ZIP creation) to ensure it stays within the designated output directory.\n- [SAFE]: Subprocess execution of system tools like ffmpeg, ffprobe, zip, and curl is handled safely with controlled arguments, avoiding shell injection risks.\n- [SAFE]: While the skill ingests untrusted data from X posts, it is primarily a visual rendering tool. The content is escaped for HTML rendering and is not interpreted as instructions by the agent, effectively mitigating indirect prompt injection risks.
Audit Metadata