granola-debug-bundle

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs legitimate diagnostic operations, such as collecting system specifications and application-specific logs, which are standard for troubleshooting tasks.
  • [COMMAND_EXECUTION]: The skill uses system commands (e.g., system_profiler, sw_vers, log) that are explicitly declared in the allowed-tools section and are used appropriately for information gathering.
  • [DATA_EXFILTRATION]: Network connectivity tests are performed using curl against the service's own domains (api.granola.ai and granola.ai). No unauthorized data transmission to third-party or unknown servers was detected.
  • [PROMPT_INJECTION]: No instructions were found that attempt to bypass safety filters or override the agent's core behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 01:20 AM