gds-retrospective

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script (resolve_customization.py) within the project's internal directory (_bmad/scripts/) to manage configuration and customization. This is a standard operation within the vendor's project framework.
  • [DATA_EXFILTRATION]: No network activity was detected. The skill reads local project files and generates a local retrospective summary without exfiltrating data.
  • [REMOTE_CODE_EXECUTION]: The skill does not download or execute code from external or unverifiable sources.
  • [PROMPT_INJECTION]: Instructions include a role-play protocol for team interaction ('Party mode'), which is consistent with its purpose and does not attempt to bypass safety constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 06:21 PM
Security Audit — agent-trust-hub — gds-retrospective