twitter-cli
Warn
Audited by Snyk on Apr 18, 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.md explicitly instructs the agent to run commands like "twitter search", "twitter feed", and "twitter tweet" which fetch public, user-generated content from twitter.com/X and directs agents to parse the CLI's --json output programmatically, so untrusted third-party tweets could be read and materially influence subsequent tool use or decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata