Skills
Navigate
skills/thedotmack/claude-mem/claude-mem-install/Gen Agent Trust Hub

claude-mem-install

Warn

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions include shell commands for software installation and configuration. Evidence: npx claude-mem install --ide cursor and variants with server URLs.
  • [EXTERNAL_DOWNLOADS]: The installation process fetches code from the public NPM registry. Evidence: npx downloads the claude-mem package before execution.
  • [REMOTE_CODE_EXECUTION]: The skill uses npx to download and immediately execute code from an external repository. Evidence: The install command runs the claude-mem package logic.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to ingest external configuration data and tokens.
  • Ingestion points: SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: Terminal access and network connectivity for tool use.
  • Sanitization: None.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 2, 2026, 08:04 PM
Security Audit — agent-trust-hub — claude-mem-install