x-keyword-comment
Warn
Audited by Snyk on Jun 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: 0.85). The skill navigates to X search results and then uses
browser-act ... get markdown/browser-act ... eval "$(python scripts/scan-search-tweets.py ...)"to extracttweetSnippet/tweet text from outsider-authored tweets (public web content on x.com) into JSON that is then used to generate replies—this is indirect prompt injection via scraped free text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata