The Agent Skills Directory

[SAFE]: The skill is a purely instructional guide for technical debugging and contains no malicious instructions or executable attack vectors.\n- [PROMPT_INJECTION]: The skill includes a 'Error Output as Untrusted Data' section that correctly identifies error messages as untrusted external content and provides specific defensive instructions to prevent the agent from executing commands or following links contained within those messages.\n- [COMMAND_EXECUTION]: The skill uses examples of standard development CLI tools, such as git bisect and pytest, for their intended purpose in verifying software behavior and does not demonstrate any unsafe command execution patterns.

systematic-debugging