easysdd-architecture-gen

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts (easysdd/tools/search-yaml.py) and standard git commands (git log). These operations are restricted to the local environment and are intended for project metadata retrieval and change tracking.
  • [DATA_EXPOSURE]: The skill reads project files, architecture documents, and source code to generate documentation. All operations are local, with no evidence of network-based exfiltration or credential harvesting.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user-supplied materials and external documents. It mitigates injection risks through a mandatory 'Phase 5' user review and a 'Phase 4' self-check that requires every claim to be anchored to specific code locations (file:line).
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 02:38 PM