twitter

Warn

Audited by Snyk on Mar 14, 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 reads public, user-generated Twitter/X content via the twitter-cli (see SKILL.md and references/commands.md: commands like "twitter feed", "twitter search", "twitter user-posts", "twitter tweet") and instructs the agent to summarize and act on that data for financial research, so untrusted third-party content can materially influence agent decisions and enable indirect prompt injection.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 14, 2026, 04:46 AM
Issues
1