daily

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the membrane CLI to perform legitimate meeting management operations such as listing rooms and running specific actions. This is the intended purpose of the skill.
  • [EXTERNAL_DOWNLOADS]: Instructions specify installing the official @membranehq/cli package from npm, which is the verified tool provided by the vendor for this integration.
  • [DATA_EXFILTRATION]: The skill implements a secure credential model, explicitly directing the agent to use managed connections rather than handling raw user API keys or tokens.
  • [METADATA_POISONING]: A minor documentation error exists in the YAML description field, which refers to CRM features like 'Leads' and 'Deals' that are unrelated to the Daily video API. This does not pose a security risk and appears to be a template artifact.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 10:02 AM