The Agent Skills Directory

[SAFE]: The skill is composed entirely of Markdown documentation and instructional prompts. No executable scripts, binaries, or configuration files that could trigger code execution were found.\n- [DATA_EXPOSURE]: The instructions suggest reading a local file named '.agents/product-marketing-context.md' to obtain business context. This is a standard method for providing project-specific information to an agent and does not involve unauthorized data access or exfiltration.\n- [PROMPT_INJECTION]: The skill uses persona-based instructions (e.g., 'You are an expert cold email writer') to define the agent's task. No malicious injection patterns or instructions to bypass safety guidelines were detected.\n- [COMMAND_EXECUTION]: No system commands, shell scripts, or dynamic execution patterns (such as the !command syntax) are present in any of the skill's files.

cold-email