xclaw

Warn

Audited by Snyk on Mar 13, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). This skill fetches live, user-generated tweets from the third-party pro.xclaw.info API (see SKILL.md "Trending Discovery" / "Recent Tweets" and xclaw.js calls like requestXClaw('/tweet/hot_tweets', '/tweet/kol_tweets', '/tweet/tweet_detail')), then ingests and uses that text/HTML to drive analyses and to generate drafts (e.g., slimTweets and the 'draft' command), so untrusted public content can materially influence agent behavior and actions.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 13, 2026, 05:27 PM
Issues
1