openevidence-cost-tuning
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of Markdown documentation and instructions with no executable scripts, shell commands, or automated installers.
- [SAFE]: All external URLs reference the official
openevidence.comdomain or its subdomains, which are directly relevant to the skill's stated purpose of evaluating OpenEvidence adoption. - [SAFE]: The instructions include multiple explicit security and privacy constraints, such as 'Never expose credentials, PHI, recordings, or unrestricted environment output' and 'Redact patient and credential data'.
- [SAFE]: The skill uses a 'least privilege' approach by directing the agent to use
WebFetchonly for first-party documentation and limitingWrite/Editoperations to user-approved destinations.
Audit Metadata