qbr-planning

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill implements business methodology for customer success planning. It does not utilize network resources or access sensitive system configuration files.
  • [COMMAND_EXECUTION]: The skill provides scripts/check-output.py, which is a utility for the agent to verify its own output quality by checking for specific markdown headers.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of customer-specific business data to generate planning artifacts.
  • Ingestion points: User-supplied business context gathered during the 'Diagnostic Questions' phase in SKILL.md.
  • Boundary markers: Not defined in the instructions.
  • Capability inventory: Execution of a local Python script (scripts/check-output.py) to read and analyze file contents.
  • Sanitization: No data sanitization is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 12:47 PM
Security Audit — agent-trust-hub — qbr-planning