skills/munolabs/skills/looker-studio/Gen Agent Trust Hub

looker-studio

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION] (LOW): The file postgresql-connection.md suggests disabling SSL for database connections if certificate issues occur. This practice reduces transport security and could potentially expose data to interception during transit between the database and Looker Studio.
  • [PROMPT_INJECTION] (LOW): The skill facilitates the ingestion of untrusted data from external PostgreSQL and Supabase databases, creating a surface for indirect prompt injection if that data is subsequently processed by an agent.
  • Ingestion points: postgresql-connection.md defines connection parameters for external data sources.
  • Boundary markers: Absent; the documentation does not provide instructions for delimiting or ignoring instructions embedded within the data.
  • Capability inventory: None; the skill consists entirely of markdown documentation and contains no scripts or executable functions.
  • Sanitization: The skill recommends best practices like SAFE_CAST and REGEXP_REPLACE in conversion-functions.md and text-functions.md for data normalization.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:30 PM