getnote-note
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the execution of the 'getnote' command-line interface to interact with a note-taking service. It includes specific guidance to prevent command injection at the shell level by recommending the use of '--content-file' or '--stdin' for handling large or complex text inputs.
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes external content, including transcripts, meeting todos, and note summaries, which presents a surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the agent context via 'getnote note', 'getnote note transcript', and 'getnote note original' commands as specified in SKILL.md.
- Boundary markers: The instructions advise the agent to retain user intent without expansion and to use strict JSON parsing, though specific delimiters for the note content itself are not explicitly defined.
- Capability inventory: The skill possesses significant capabilities including the ability to update, delete, and publicly share content using the 'getnote note update/delete/share' commands.
- Sanitization: The skill enforces strict output validation by requiring JSON results ('-o json') and checking for specific success fields before confirming actions to the user.
Audit Metadata