positioning-truth-tracer
Warn
Audited by Snyk on Jul 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The skill explicitly allows pulling competitor messaging via runtime web scraping/search connectors (firecrawl/tavily) and then uses that scraped free-form text to re-test the onlyness statement, which can be outsider-authored content injected into the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata