The Agent Skills Directory

[PROMPT_INJECTION]: The skill contains phrases typically associated with prompt injection, such as "Ignore instructions" and "Ignore all previous instructions". However, these are documented as examples for regression testing and defense mechanisms, rather than instructions to the agent to override its behavior.
[REMOTE_CODE_EXECUTION]: The technical templates provided (Python code snippets) are educational and intended for local development workflows. They do not contain any instructions for the agent to execute untrusted remote code.
[SAFE]: No network exfiltration, sensitive file access, or hardcoded credentials were detected. The skill's behavior is consistent with its stated purpose as a prompt design specialist.

Prompt Engineer