google-maps-reviews-scraper

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Ingestion of external CSV data creates a surface for indirect prompt injection. \n- Ingestion points: Processes business data and review text from CSV files provided by the user (SKILL.md). \n- Boundary markers: Absent. No specific markers or warnings are used to delimit data from instructions. \n- Capability inventory: None. The skill consists only of natural language instructions and lacks executable scripts or network access tools. \n- Sanitization: Absent. There is no logic provided to filter or escape content within the CSV fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 05:16 AM
Security Audit — agent-trust-hub — google-maps-reviews-scraper