discovery-explore

Warn

Audited by Snyk on Feb 28, 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). The SKILL.md explicitly instructs scraping and monitoring of public X/Twitter pages (e.g., scripts/scrapeSearch.js, src/exploreScraper.js, src/trendingTopicMonitor.js targeting x.com/explore, x.com/hashtag/TAG and search results) and uses that untrusted user-generated content (tweets) to drive monitoring, analysis, and content-posting decisions, so external content can materially influence agent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 09:53 AM