tweetclaw-twitter-automation-cn

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @xquik/tweetclaw package from the official NPM registry and references documentation hosted on GitHub and the Xquik domain.
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the openclaw command-line interface to install plugins (openclaw plugins install), inspect runtime configuration (openclaw plugins inspect), and query skill information (openclaw skills info).
  • [PROMPT_INJECTION]: The skill ingests and processes untrusted data from external sources, creating an indirect prompt injection attack surface.
  • Ingestion points: Scraped tweets, search results, and Direct Messages from the X/Twitter platform (SKILL.md).
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the ingested Twitter content.
  • Capability inventory: The agent has the ability to post tweets, send DMs, create webhooks, and execute plugin management commands via the openclaw CLI (SKILL.md).
  • Sanitization: No explicit sanitization, filtering, or validation of the external content is mentioned in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 03:37 PM
Security Audit — agent-trust-hub — tweetclaw-twitter-automation-cn