granola
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill suggests installing the
granola-clitool from the author's GitHub repository (github.com/lox/granola-cli). - [COMMAND_EXECUTION]: The skill utilizes the
granola-clibash tool to retrieve and manage meeting data. - [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by processing external data from meeting transcripts and notes.
- Ingestion points: Meeting content is retrieved via
granola-cli query,meetings view, andmeetings transcriptcommands as defined inSKILL.md. - Boundary markers: No specific delimiters or instructions are used to separate meeting content from agent instructions.
- Capability inventory: The skill is authorized to execute
Bashcommands within thegranola-cli:*scope. - Sanitization: There is no evidence of content sanitization or filtering before the data is processed by the agent.
Audit Metadata