gsd-explore
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a workflow for ideation and task organization. No malicious patterns, such as obfuscation, unauthorized data access, or remote code execution, were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill accepts a user-provided topic for exploration. While this represents a surface for user input, it is consistent with the skill's primary purpose and relies on the agent's standard safety guardrails during the ideation process. Evidence: The
gsd-explorecommand accepts an optional topic argument for Socratic ideation.
Audit Metadata