governance-intel

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches governance data (proposals, votes, space metadata) from Snapshot's official public GraphQL API (hub.snapshot.org). This is a well-known service for DAO governance and the integration is performed using standard HTTP requests with no authentication required.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from Snapshot proposals (titles, descriptions, and choices).
  • Ingestion points: Data is fetched via GraphQL in proposal_scanner.py, voting_analyzer.py, and dao_health.py.
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the skill's guidelines.
  • Capability inventory: The skill is limited to data processing and JSON output. It lacks dangerous capabilities such as file system writes, shell command execution, or secondary network requests based on fetched content.
  • Sanitization: The scripts perform type validation and basic formatting but do not explicitly sanitize or escape the text content before it is passed to the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 07:52 PM
Security Audit — agent-trust-hub — governance-intel