signal-scanner
Warn
Audited by Snyk on Jun 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). Runtime path: the skill runs
exa-search__web_search_advanced_exaqueries (web/news/tweet categories) and ingests the fetched page/snippet text into the agent to score and report signals, which is outsider-authored free text from public web/social sources.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata