twitter-to-obsidian

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly navigates to and snapshots public Twitter/X pages using Chrome DevTools MCP (mcp__chrome-devtools__navigate_page and mcp__chrome-devtools__take_snapshot) and then reads and structures user-generated Twitter/X content, exposing the agent to untrusted third-party content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.80). The skill explicitly navigates to and snapshots user-provided Twitter/X pages at runtime (e.g., https://x.com/0xYuker/status/2013094122656334136), and the fetched page content is injected into the agent's analysis/summarization context so external page content can directly influence prompts/outputs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:06 PM