The Agent Skills Directory

[NO_CODE]: The skill consists entirely of natural language instructions and structural guidelines for improving writing style. It does not contain any scripts, binaries, or executable commands.
[PROMPT_INJECTION]: No attempts to override agent behavior, bypass safety filters, or extract system prompts were detected. The instructions are focused on applying neurological and storytelling principles to text.
[DATA_EXFILTRATION]: The skill does not perform network operations, hardcode credentials, or attempt to access sensitive local files such as SSH keys or environment configurations.
[OBFUSCATION]: The content is clear and readable. No hidden characters (e.g., zero-width spaces), Base64 encoding of commands, or homoglyph attacks are present.
[REMOTE_CODE_EXECUTION]: There are no commands for downloading external scripts, installing third-party packages, or dynamic execution of untrusted code.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to process user-provided text for editing purposes, it lacks any exploitable capabilities (such as shell access, file-writing, or network requests) that could be triggered by malicious instructions embedded in that text.

resonance-engine