desearch-x-search

Warn

Audited by Snyk on Mar 10, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and ingests real-time, user-generated X/Twitter posts via the Desearch API (see SKILL.md and scripts/desearch.py where api_request calls hit /twitter endpoints and format_tweets prints the returned posts), so untrusted third-party content is read and could influence subsequent agent decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 03:07 PM