twitter-automation
Warn
Audited by Snyk on Feb 15, 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). The skill uses Twitter toolkit endpoints such as TWITTER_RECENT_SEARCH, TWITTER_FULL_ARCHIVE_SEARCH, and various user/post lookup endpoints which fetch public, user-generated tweets and profiles that the agent is expected to read and process, exposing it to untrusted third‑party content and potential indirect prompt injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill requires connecting to an MCP server at https://rube.app/mcp and explicitly instructs calling RUBE_SEARCH_TOOLS at runtime to fetch tool schemas and invoke remote toolkit actions, so runtime-fetched content from that URL can directly control agent behavior and execute remote code.
Audit Metadata