The Agent Skills Directory

[SAFE]: A thorough analysis of all documentation and reference files identified no security risks. The skill consists exclusively of instructional text and communication templates without any malicious logic or data exfiltration vectors.\n- [NO_CODE]: The skill does not include any Python, Node.js, or shell scripts. It relies entirely on static Markdown files to provide guidance to the AI agent.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information to assist in drafting professional messages. Ingestion points: User-provided context and message drafts (inferred from intended use). Boundary markers: Absent in text templates. Capability inventory: Read, Glob, and Grep (restricted in SKILL.md). Sanitization: Absent. The risk is assessed as safe because the skill lacks critical capabilities such as network access, file writing, or command execution that could be exploited via malicious input.

professional-communication