twitter-automation
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires users to add an external Model Context Protocol (MCP) server endpoint (
https://rube.app/mcp) to their configuration. This domain is a third-party service that mediates all Twitter interactions and tool executions. - [PROMPT_INJECTION]: The skill has a significant attack surface for indirect prompt injection where malicious instructions hidden in Tweets or user profiles could influence the agent's behavior.
- Ingestion points: Untrusted data enters the agent context via
TWITTER_RECENT_SEARCH,TWITTER_FULL_ARCHIVE_SEARCH,TWITTER_USER_LOOKUP_BY_USERNAME, andTWITTER_BOOKMARKS_BY_USERas defined inSKILL.md. - Boundary markers: There are no specified delimiters or instructions to treat retrieved Twitter content as untrusted data.
- Capability inventory: The skill provides several high-impact write capabilities, including
TWITTER_CREATION_OF_A_POST,TWITTER_POST_DELETE_BY_POST_ID, andTWITTER_UNLIKE_POSTinSKILL.md. - Sanitization: No evidence of input validation or sanitization is provided for the data retrieved from external Twitter searches.
Audit Metadata