twitter-automation
Warn
Audited by Snyk on Mar 7, 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 includes apps that fetch and read user-generated Twitter/X content (e.g., "Get User Profile"
x/user-getand "Get Tweet Details"x/post-get) as listed in SKILL.md, which would allow untrusted third‑party tweets/profiles to be ingested and influence actions like liking, retweeting, following, or sending DMs.
Audit Metadata