The Agent Skills Directory

[SAFE]: The skill is purely informational and instruction-based, focused on the professional task of writing cold emails. It does not contain executable code, shell commands, or network requests.
[PROMPT_INJECTION]: No evidence of prompt injection or instructions to bypass safety guidelines. The guidance provided is strictly focused on tone, structure, and effectiveness of marketing copy.
[DATA_EXFILTRATION]: The skill does not attempt to access sensitive files (like SSH keys or AWS credentials) or exfiltrate data to external servers. It suggests reading local product marketing context files (.agents/product-marketing.md) to inform the writing process, which is expected and safe behavior.
[REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote scripts. No package managers or dynamic code execution functions are utilized.
[COMMAND_EXECUTION]: No shell commands, subprocess calls, or privilege escalation attempts were found in any of the skill files.
[OBFUSCATION]: All content is in plain text. No Base64, zero-width characters, or other encoding techniques are used to hide malicious instructions or URLs.

cold-email