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
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 12, 2026, 10:32 AM
Issues
1