recap
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes data from agent session history and memory recall services, which could contain instructions from previous interactions. Ingestion points: Data returned from session history and memory recall tools in SKILL.md. Boundary markers: Not present; the session data is interpolated directly into the summary context. Capability inventory: Performs network operations (HTTP GET/POST) to retrieve data. Sanitization: No content filtering or instruction-bypass protection is applied to the retrieved history.
- [EXTERNAL_DOWNLOADS]: The skill is designed to fetch data from a service URL specified by the $AGENTMEMORY_URL environment variable as a fallback when local MCP tools are unavailable.
Audit Metadata