The Agent Skills Directory

[PROMPT_INJECTION]: No attempts to override system instructions, bypass safety guidelines, or extract system prompts were detected in the skill instructions.
[DATA_EXFILTRATION]: The skill does not access sensitive files or perform network operations. No hardcoded credentials or secrets were found.
[REMOTE_CODE_EXECUTION]: There are no references to external scripts, remote downloads, or the execution of untrusted code.
[COMMAND_EXECUTION]: The skill does not utilize shell commands, subprocesses, or any form of dynamic code execution.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user input (rough prompts) to generate an optimized version. While this creates an ingestion surface for potential prompt injection, the skill lacks the necessary capabilities (such as file system access or network tools) to act upon malicious instructions if they were present in the user data.
[SAFE]: All instructions and metadata are consistent with the stated purpose of prompt optimization and follow standard instructional patterns.

prompt-optimizer