bmad-cis-agent-creative-problem-solver

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill does not contain any malicious patterns such as remote code execution, unauthorized data exfiltration, or persistence mechanisms.
  • [PROMPT_INJECTION]: The instructions include persona-consistency constraints, such as the requirement to not break character until dismissed. These are standard instructional prompts for role-play and do not attempt to bypass core AI safety filters or guidelines.
  • [DATA_EXFILTRATION]: The skill accesses local project files (config.yaml and project-context.md) to resolve user preferences and project-specific standards. This is a local data ingestion pattern for context-aware agents and does not involve sending data to external or untrusted domains.
  • [COMMAND_EXECUTION]: The skill restricts its capability invocation to an explicit table of registered skills, specifically bmad-cis-problem-solving, which prevents the agent from executing arbitrary or unintended commands.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 09:53 AM