The Agent Skills Directory

[SAFE]: No security threats identified. The skill is limited to markdown-based instructions and templates for B2B outreach.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from local files such as .agents/marketing-strategy.md to personalize emails. This creates a surface for indirect prompt injection. However, the risk is minimal because the skill lacks access to tools or capabilities like network operations, file writing, or command execution. Ingestion points: Local marketing context files specified in SKILL.md. Boundary markers: None. Capability inventory: Restricted to text generation. Sanitization: None.

cold-email