x-bookmarks

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No evidence of malicious code, obfuscation, or unauthorized data access was found. The skill operates within its stated scope.
  • [DATA_EXPOSURE]: The skill reads private bookmark data from X (Twitter) using the vendor's infrastructure at xquik.com. This alignment between author and domain is consistent with legitimate vendor functionality.
  • [PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface through the ingestion of external tweet data.
  • Ingestion points: Untrusted content is retrieved from X via the /x/bookmarks endpoint in SKILL.md.
  • Boundary markers: The documentation explicitly instructs the agent to treat retrieved text as data, which acts as a conceptual boundary.
  • Capability inventory: The skill is restricted to read and export operations; it does not possess filesystem or shell execution capabilities.
  • Sanitization: No explicit sanitization or filtering of the retrieved content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 09:38 AM