The Agent Skills Directory

[COMMAND_EXECUTION]: The skill constructs a shell command by interpolating user-provided inputs for <type> and <tag> into the npx @codevoyant/agent-kit mem find command. A malicious user could provide input containing shell meta-characters (e.g., ;, &, |, or backticks) to execute arbitrary commands on the host system.
[EXTERNAL_DOWNLOADS]: The skill uses the npx command to download and run the @codevoyant/agent-kit package directly from the npm registry during execution.
[REMOTE_CODE_EXECUTION]: By combining the execution of remote code via npx with unsanitized shell interpolation of user input, the skill presents a significant risk of arbitrary code execution.

mem-find