Access and process Granola meeting notes and transcripts via the granola CLI (MCP-backed). Use when pulling meeting data, analyzing transcripts, backfilling meetings, or any task involving Granola meeting content.
84%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The workflow ingests meeting notes and transcripts from Granola, which record conversations with external participants whose untrusted statements can enter the agent's context.
joelhooks/joelclaw
1fb2468
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.