The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill incorporates external context from project files and user input into its email generation process.
Ingestion points: The skill instructions in SKILL.md explicitly direct the agent to read .agents/product-marketing.md or .claude/product-marketing.md to inform its outreach drafts.
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined to protect the agent from malicious instructions that could be hidden within the context files.
Capability inventory: The skill is limited to generating text; it does not include commands for network operations, file writing, or subprocess execution.
Sanitization: The content from context files is used as-is for generating drafts without validation or filtering.
[SAFE]: No malicious patterns such as obfuscation, credential theft, or remote code execution were detected. The skill consists of legitimate markdown documentation and copywriting frameworks.

cold-email