The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses bash -c to wrap curl commands. This ensures that environment variables are correctly handled within shell pipelines.
[EXTERNAL_DOWNLOADS]: It communicates with https://public-api.granola.ai to retrieve meeting summaries and transcripts. This is the expected and documented API for the service.
[PROMPT_INJECTION]: The ingestion of meeting notes and transcripts poses an indirect prompt injection risk if the external content contains malicious instructions. * Ingestion points: meeting notes and transcripts from the Granola API. * Boundary markers: none provided in the skill instructions. * Capability inventory: shell access via bash and network requests via curl. * Sanitization: no evidence of text sanitization for the fetched meeting data.
[SAFE]: No obfuscation, hardcoded credentials, or unauthorized network operations were found in the skill.

granola