tweetclaw-x-twitter-automation

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the @xquik/tweetclaw plugin, which is an external dependency required for the core Twitter automation functionality.\n- [PROMPT_INJECTION]: The skill's primary function involves processing external content from X/Twitter (tweets and replies), which creates an inherent surface for indirect prompt injection attacks.\n
  • Ingestion points: Untrusted data is ingested when searching tweets or monitoring replies in SKILL.md.\n
  • Boundary markers: While the skill defines a structured output format for findings, it does not specify explicit delimiters or isolation instructions for the raw external data processed.\n
  • Capability inventory: The agent has capabilities to perform significant account actions including posting tweets and sending direct messages through the plugin.\n
  • Sanitization: No specific sanitization or filtering logic is described for the retrieved tweet content prior to analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 02:55 AM
Security Audit — agent-trust-hub — tweetclaw-x-twitter-automation