xurl

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's documentation recommends installing the 'xurl' CLI utility from the '@xdevplatform' organization via npm, Homebrew, or Go. These external packages are necessary for the skill's documented CLI functionality but originate from a source not explicitly linked to the skill author.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through data ingested from the X API.
  • Ingestion points: The 'xurl.js' file contains several methods (e.g., search, getTweet, getUserTweets) that fetch content from external users.
  • Boundary markers: There are no boundary markers or instructions to treat retrieved data as untrusted content, which may lead the agent to follow instructions embedded in tweets.
  • Capability inventory: The skill possesses significant account-level permissions, including posting tweets, sending direct messages, and following/unfollowing users.
  • Sanitization: Data retrieved from the API is returned as raw text and is not sanitized or filtered before being presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 05:12 AM