geopandas

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documents how to read geospatial data from external URLs and remote storage services like Amazon S3 and Azure Blob Storage using the geopandas.read_file function.
  • [PROMPT_INJECTION]: The skill describes processing external data formats which constitutes an ingestion surface for indirect prompt injection. 1. Ingestion points: gpd.read_file and gpd.read_postgis found in SKILL.md and references/data-io.md. 2. Boundary markers: None present. 3. Capability inventory: File writing via to_file and database operations via to_postgis in references/data-io.md. 4. Sanitization: No sanitization or validation of external data is specified.
  • [CREDENTIALS_UNSAFE]: The documentation provides a template connection string for PostGIS databases which uses generic placeholders for user credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 11:30 PM
Security Audit — agent-trust-hub — geopandas