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