discover

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates as a stage in a larger PRD-taskmaster pipeline, managing discovery notes and phase transitions through a structured process.
  • [SAFE]: All tool usage, including MCP plugins like mcp__plugin_prd_go, is consistent with the skill's purpose and uses restricted execution logic (e.g., user-invocable: false).
  • [SAFE]: The autonomous mode logic is well-contained, using Git commits as audit trails and focusing on documented context files for project calibration.
  • [SAFE]: No instances of prompt injection, data exfiltration, or obfuscated code were found during the analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 11:14 AM
Security Audit — agent-trust-hub — discover