The Agent Skills Directory

[NO_CODE]: The skill consists entirely of natural language instructions to define an AI persona. There are no scripts, binaries, or shell commands included in the package.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided text (drafts and essays). While this is a theoretical attack surface, the instructions focus on editorial critique and include specific boundaries against executing or silently altering code or technical semantics. The instructions direct the agent to flag potential issues for the user rather than processing them as commands.
[SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or unauthorized command execution was found. The skill does not request any sensitive permissions or tool access.

editorial-review