memmachine

Pass

Audited by Gen Agent Trust Hub on Oct 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill operates on long-term memory data which could potentially contain malicious instructions intended to influence the agent (indirect prompt injection). This is a standard risk for memory-management skills. The skill mitigates this surface by instructing the agent to resolve specific project/session scopes and requiring explicit user approval before any memory mutations (writes/deletes) or external service connections.
  • Ingestion points: Memory payloads retrieved from the MemMachine server and configuration files.
  • Boundary markers: The skill relies on structured instructions requiring the agent to pause for approval before acting on retrieved data.
  • Capability inventory: The agent has access to Bash, Read, Grep, and Glob tools.
  • Sanitization: The provided preflight.py utility verifies the integrity of the tool source code, though it does not perform runtime sanitization of individual memory payloads.
  • [SAFE]: The skill demonstrates a high security posture by including a defensive preflight.py script designed to verify the local environment. This script implements several security controls:
  • Path Sanitization: It contains a blocklist of sensitive file names and stems (e.g., .ssh, .aws, .env, id_rsa, token, secret) to prevent accidental data exposure.
  • Secure Path Traversal: It uses os.O_NOFOLLOW and directory file descriptors (dir_fd) to prevent symbolic link attacks during file verification.
  • Integrity Checking: It validates the source code against a manifest of SHA-256 hashes (references/source.json) to ensure the agent is using verified versions of the integration logic.
  • Least Privilege: The instructions explicitly gate all potentially dangerous actions (installations, service startup, MCP registration, data deletion) behind mandatory human approval.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 30, 2026, 09:02 AM