Skills
skills/ruvnet/claude-flow/memory-search/Gen Agent Trust Hub

memory-search

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute search commands via npx. User-provided queries are interpolated into these commands to facilitate retrieval.
  • [EXTERNAL_DOWNLOADS]: Fetches the @claude-flow/cli and ruvector packages from the NPM registry. These tools are associated with the vendor's ecosystem and used for their intended search functionality.
  • [PROMPT_INJECTION]: Ingests user queries that are interpolated into shell commands. This creates an indirect ingestion surface where the agent is instructed to use external input within a shell context, though the primary intent is standard functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 01:22 PM
Security Audit — agent-trust-hub — memory-search