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 manifest command 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 manifest command 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 mi command.
  • Sanitization: Absent. The manifest data is not sanitized or filtered before being presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 06:18 AM
Security Audit — agent-trust-hub — memory-manifest