Skills
Navigate
skills/claude-office-skills/skills/Twitter/X Automation/Gen Agent Trust Hub

Twitter/X Automation

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data from Twitter/X, such as mentions, DMs, and search results.
  • Ingestion points: The skill utilizes twitter_search and triggers based on being mentioned or receiving a new_follower to ingest data from the Twitter platform.
  • Boundary markers: There are no explicit instructions or delimiters defined to separate untrusted external content from the agent's core instructions.
  • Capability inventory: The skill has the ability to post tweets (twitter_post) and send direct messages (twitter_dm) via the social-mcp server.
  • Sanitization: No specific sanitization or filtering logic is described for the content fetched from the platform before it is used to generate responses.
  • [SAFE]: The JavaScript code snippets provided in the 'API Integration' section are documentation examples for tool usage and do not involve dynamic execution or remote code downloads.
  • [SAFE]: No hardcoded credentials, sensitive file access, or unauthorized network exfiltration attempts were found. All network interactions are scoped to the intended Twitter/X API functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 12:52 AM