The Agent Skills Directory

[SAFE]: The skill facilitates management of Get笔记 knowledge bases via a dedicated CLI tool. All described functionalities align with the stated purpose of knowledge base management, and no evidence of malicious intent, credential theft, or unauthorized data exfiltration was found.
[COMMAND_EXECUTION]: The skill defines a set of commands to be executed via the getnote CLI. These commands are appropriately scoped to knowledge base operations such as listing, creating, adding, and removing items. The use of user-supplied arguments (like topic IDs and names) within these commands is standard for this type of agent extension.
[PROMPT_INJECTION]: While the skill ingests external content from knowledge bases (e.g., blogger content and live transcripts), which is a characteristic surface for indirect prompt injection, this behavior is a core requirement of the skill's functionality. 1. Ingestion points: getnote kb blogger-content and getnote kb live. 2. Boundary markers: Not explicitly defined. 3. Capability inventory: getnote CLI commands for content modification. 4. Sanitization: Not explicitly defined. Given the context of a personal knowledge management tool, this surface is considered a standard operational risk rather than a specific finding for this skill.

getnote-kb