The Agent Skills Directory

[SAFE]: The skill is a collection of educational Markdown documents and templates for professional communication.
[NO_CODE]: The skill does not contain any scripts, binaries, or automated tasks; it relies solely on text-based reference material.
[DATA_EXPOSURE]: No hardcoded credentials, secrets, or sensitive system file paths were found in the templates or documentation.
[INDIRECT_PROMPT_INJECTION]: The skill acts as a template for the agent when processing user-supplied communication (e.g., drafting emails). While this represents an ingestion surface for potential indirect prompt injection, the skill's environment is restricted to read-only tools (Read, Glob, Grep) as defined in the YAML frontmatter, which prevents any malicious instructions in the processed data from performing unauthorized network or write operations. Evidence Chain:
Ingestion points: User-supplied messages (emails, chats) that the agent is asked to refine using the skill's frameworks.
Boundary markers: None present in the templates.
Capability inventory: Restricted to read-only file system operations (Read, Glob, Grep).
Sanitization: None identified.

professional-communication