The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified. The skill is purely instructional.- [PROMPT_INJECTION]: The instructions define a specific semantic transformation task and do not attempt to override the AI's core safety guidelines or ignore previous instructions.- [DATA_EXFILTRATION]: No hardcoded credentials, sensitive file paths, or network exfiltration patterns were detected. The skill does not communicate with external domains.- [REMOTE_CODE_EXECUTION]: There are no remote scripts, package installations, or execution of untrusted code.- [COMMAND_EXECUTION]: The skill contains no shell commands, subprocess calls, or system-level operations.- [INDIRECT_PROMPT_INJECTION]: The skill acts as a transformer for user input but lacks the necessary capabilities (such as file-writing or network access) to be exploited by malicious data.

question-forge