ulw-research
Warn
Audited by Snyk on Jul 19, 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). SKILL.md instructs the skill to perform runtime web research/browsing (e.g., “Web (librarian)… fetch the full page for every result that matters” and “Browsing… loads the
ultimate-browsingskill”), which would ingest outsider-authored free text from public web pages into worker messages and then back into the orchestrator’s LLM context via message text (EXPAND/CLAIMS/observation candidates).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata