The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and run the repomix package from the npm registry and provides instructions for using a Docker image from ghcr.io.
[COMMAND_EXECUTION]: The skill executes CLI commands such as npx, docker, git, and find to traverse directories and process codebases.
[PROMPT_INJECTION]: By aggregating code from local or remote repositories for LLM analysis, the tool creates a surface for indirect prompt injection where instructions embedded in the processed code could potentially influence the analyzing agent.
[DATA_EXFILTRATION]: The core function of the tool is to consolidate repository data for analysis by external AI models. The skill documentation highlights a security feature that uses Secretlint to detect and block the inclusion of sensitive credentials in the generated output file.

repomix