schema-migration

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a process for the agent to ingest and compare external specification files from the project's openspec/ directory. This creates a surface for indirect prompt injection where malicious instructions embedded in the data model specs could potentially influence the agent's behavior during migration testing.\n
  • Ingestion points: The agent reads delta specs from openspec/changes/<change-name>/specs/ and archived specs from openspec/specs/.\n
  • Boundary markers: The skill does not explicitly instruct the agent to use delimiters or 'ignore embedded instructions' markers when processing these external files.\n
  • Capability inventory: The skill involves generating migration code and executing it via Model Context Protocol (MCP) tools within a development environment.\n
  • Sanitization: No specific content sanitization or validation logic is defined for the external specification data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 01:44 PM
Security Audit — agent-trust-hub — schema-migration