session-create
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill performs standard session initialization and telemetry recording using an internal database tool.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface by ingesting parameters like 'agentName' and 'storyId' and emitting them in a structured block for worker agents. However, this is consistent with its telemetry purpose. Ingestion points: parameters in SKILL.md. Boundary markers: Absent. Capability inventory: Database write via mcp__postgres-knowledgebase__sessionCreate. Sanitization: Absent.
Audit Metadata