The Agent Skills Directory

[Prompt Injection] (SAFE): The skill defines a specific writing persona and style constraints. There are no attempts to bypass safety filters, extract system prompts, or override core agent instructions.
[Data Exfiltration] (SAFE): No network operations (curl, wget, fetch) or sensitive file path access (credentials, SSH keys) were found in the skill files.
[Remote Code Execution] (SAFE): The skill consists entirely of Markdown text. There are no package installation commands or remote script executions.
[Indirect Prompt Injection] (LOW): The skill processes user-provided text to rewrite it in a specific style. However, because the skill has no 'capability inventory' (it cannot write files, execute commands, or access the network), there is no risk of a downstream attack through malicious data.
[Obfuscation] (SAFE): No encoded strings (Base64), zero-width characters, or homoglyphs were detected in the text.

beary-style