memory-manifest
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute the
mi cortex manifestcommand to retrieve a summary of connected data sources and memory content. This is a standard discovery tool for the Mitosis memory system. - [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection (Category 8) by processing summary data from the memory manifest.
- Ingestion points: Output from the
mi cortex manifestcommand documented in SKILL.md. - Boundary markers: Absent. The instructions do not specify how the agent should delimit or isolate the manifest content.
- Capability inventory: The skill performs read-only discovery using the
micommand. - Sanitization: Absent. The manifest data is not sanitized or filtered before being presented to the agent.
Audit Metadata