distill-memory

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing 'nmem-cli' via pip. This is a vendor-specific tool used to support the primary functionality of the skill.
  • [COMMAND_EXECUTION]: The skill uses shell commands to interact with the 'nmem' utility for adding and updating memory entries.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies and summarizes breakthroughs from user conversations to store as memory.
  • Ingestion points: The agent monitors user interaction for 'breakthroughs', 'decisions', or 'lessons' (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used during the summarization process.
  • Capability inventory: The skill can execute shell commands via the 'nmem' CLI tool.
  • Sanitization: There is no evidence of specific sanitization or escaping of the user-provided breakthrough content before it is passed to the shell command.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 02:13 AM