launch-copy
Warn
Audited by Snyk on Jul 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow includes “visit the live site with the
browseskill” and “ground from the live site (viabrowse), README, and product docs,” which can ingest outsider-authored free text from public web pages into the LLM context for grounding.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata