session-create

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses a specific, authorized MCP tool (mcp__postgres-knowledgebase__sessionCreate) for its core functionality, which is limited to logging session metadata (agent identity, story context, and token usage).
  • [SAFE]: No evidence of prompt injection, obfuscation, or persistence mechanisms was found. The instructions are transparent and focused on workflow telemetry.
  • [SAFE]: No hardcoded credentials or sensitive file access patterns were detected. All parameters (agentName, storyId, phase) are standard metadata fields for session tracking.
  • [SAFE]: The skill implements graceful degradation, ensuring that failures in the database connection or the telemetry tool do not block or compromise the agent's primary execution tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 09:46 PM