sourcecoop

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFECREDENTIALS_UNSAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill includes instructions to verify and configure AWS profiles for Source Cooperative by checking ~/.aws/credentials and managing local .env files. These activities are limited to the specific 'source' profile required for the service.
  • [COMMAND_EXECUTION]: Orchestrates workflows using the portolan CLI and standard shell commands (grep, cat, mkdir, mv) for data organization and cataloging.
  • [DATA_EXFILTRATION]: Directs data to s3://us-west-2.opendata.source.coop/, the official endpoint for Source Cooperative, a well-known open data commons managed by the Radiant Earth Foundation.
  • [PROMPT_INJECTION]: The skill processes metadata.yaml files to generate documentation. While this creates a surface for indirect prompt injection, the skill uses validation tools to maintain schema integrity.
  • Ingestion points: User-provided geospatial files and metadata.yaml.
  • Boundary markers: Not specified in the current skill instructions.
  • Capability inventory: File system writes, command execution, and network uploads.
  • Sanitization: Uses the portolan metadata validate command to enforce metadata standards.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 07:53 PM
Security Audit — agent-trust-hub — sourcecoop