twitter-automation

Warn

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the user to add an external MCP server from a remote URL (https://rube.app/mcp) during setup. This creates a functional dependency on an external service that is not identified as a standard well-known provider or trusted organization.
  • [INDIRECT_PROMPT_INJECTION]: The skill presents a vulnerability surface for indirect prompt injection by processing untrusted data from a public social network while maintaining high-impact capabilities.
  • Ingestion points: Untrusted data enters the agent context via Twitter search results (TWITTER_RECENT_SEARCH, TWITTER_FULL_ARCHIVE_SEARCH) and user profile data (TWITTER_USER_LOOKUP_BY_USERNAME).
  • Boundary markers: The instructions do not define delimiters or provide guidance to the agent to ignore instructions that might be embedded within the retrieved tweets or user bios.
  • Capability inventory: The skill provides access to tools capable of state-changing actions, including creating posts (TWITTER_CREATION_OF_A_POST), uploading media, and managing account bookmarks and lists.
  • Sanitization: There is no description of sanitization, filtering, or validation of the external content before it is processed by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 1, 2026, 06:21 PM
Security Audit — agent-trust-hub — twitter-automation