The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl to interact with a local API endpoint (http://localhost:8000) and docker commands (docker logs, docker inspect, docker exec) to monitor and verify agent behavior in a local container.
[PROMPT_INJECTION]: The skill instructions include references to testing for prompt injection ('adversarial probes', 'injection / scope' failures), but these are part of a testing methodology designed to harden agents against such attacks, not to perform them against the user or the host platform.

improve-agent