twitter-automation

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by retrieving and processing content from external Twitter sources.
  • Ingestion points: Untrusted data enters the agent context via tools like TWITTER_RECENT_SEARCH, TWITTER_BOOKMARKS_BY_USER, and TWITTER_POST_LOOKUP_BY_POST_ID as documented in SKILL.md.
  • Boundary markers: There are no instructions or delimiters provided to differentiate external tweet content from system instructions or to warn the agent about embedded commands.
  • Capability inventory: The skill enables significant write operations, including TWITTER_CREATION_OF_A_POST, TWITTER_POST_DELETE_BY_POST_ID, and TWITTER_UNLIKE_POST.
  • Sanitization: No sanitization or content validation is mentioned for the retrieved data before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill requires the configuration of a remote third-party service.
  • Evidence: The documentation instructs users to add https://rube.app/mcp as an MCP server. This endpoint is responsible for providing tool schemas and managing Twitter OAuth connections.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 07:56 AM