The Agent Skills Directory

[PROMPT_INJECTION]: No attempts to override agent instructions or bypass safety filters were detected. The instructions are strictly focused on task-oriented copywriting workflows.
[DATA_EXFILTRATION]: The skill does not access sensitive files (e.g., credentials, SSH keys) or perform any network operations that could exfiltrate data.
[REMOTE_CODE_EXECUTION]: There are no commands to download or execute external scripts. The skill relies entirely on local markdown reference files.
[INDIRECT_PROMPT_INJECTION]: The skill processes a user-provided 'brief' as input. While this is untrusted data, the skill does not possess dangerous capabilities (such as file-writing or network access) that could be exploited through injection, making the surface area safe.
[OBFUSCATION]: No obfuscated text, encoded strings, or hidden URLs were found in the provided files.
[DYNAMIC_CONTEXT_INJECTION]: No dynamic execution patterns (such as shell commands embedded in the markdown) were detected.

marketing-copy