The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Uses npx to download and execute the latest version of the @claude-flow/cli package from the NPM registry.
[COMMAND_EXECUTION]: Employs the Bash tool to run command-line operations for searching and managing memory within the AgentDB ecosystem.
[PROMPT_INJECTION]: The skill processes untrusted user input via the <query> argument and interpolates it into bash commands. This presents an indirect prompt injection surface where a malicious query could attempt to execute arbitrary shell commands.
Ingestion points: User-supplied <query> string in the argument-hint and CLI examples.
Boundary markers: None identified; input is directly placed within command strings.
Capability inventory: Access to Bash and multiple agentdb database management tools.
Sanitization: No explicit sanitization or escaping logic is described in the skill instructions.

agentdb-query