data-specialist
Warn
Audited by Snyk on Mar 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's included reference docs (e.g., references/cursor_rules_crewai.md) explicitly show agents/tasks using web-search and scraping tools ("Scrape website A", SerperDevTool) and other refs (e.g., references/cursor_rules_duckdb.md) demonstrate reading external S3/parquet files, indicating the agent is expected to ingest untrusted public web/storage content that can influence subsequent decisions and tool use.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata