getnote-note
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
getnoteCLI to perform operations such as saving, listing, and updating notes. Use of the CLI requires pre-installation and authentication on the local system. - [DATA_EXFILTRATION]: The skill is designed to read local files (images) and URL content to upload them to the Get笔记 service. This behavior is consistent with the skill's primary function of note management.
- [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface through the ingestion of external data from the note-taking service.
- Ingestion points: Note content, titles, and summaries retrieved using
getnote note <id>andgetnote notesas described in SKILL.md. - Boundary markers: Absent. No instructions are provided to the agent to delimit or ignore potentially malicious instructions embedded within retrieved note data.
- Capability inventory: The agent has the ability to delete notes (
getnote note delete) and modify note content or tags (getnote note update) based on information retrieved from the service. - Sanitization: Absent. The skill does not implement any validation or filtering of external note content before it is processed by the agent.
Audit Metadata