brainstorm-search-plan

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's instructions and logic focus entirely on orchestrating a conversation and gathering facts. No malicious commands, obfuscated content, or unauthorized data access patterns were identified.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted data from the user and the /search skill.
  • Ingestion points: The skill ingests fuzzy user requests and external factual data retrieved via the /search skill in Phase 2.
  • Boundary markers: No specific delimiters or safety instructions are defined for processing search results or user input.
  • Capability inventory: The skill utilizes AskUserQuestion, /search, EnterPlanMode, and ExitPlanMode to manage the planning process, and integrates with /task or /design for final execution.
  • Sanitization: The skill relies on a mandatory human-in-the-loop checkpoint via the ExitPlanMode approval gate, which ensures that the final plan is reviewed by the user before any implementation begins.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 03:29 AM
Security Audit — agent-trust-hub — brainstorm-search-plan