rehabilitation-analyzer
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION]: The skill is restricted to reading and writing local files within defined paths (e.g., data/rehabilitation-tracker.json). It contains no network-enabled tools like curl or wget, and no external domains are referenced for data transmission.- [PROMPT_INJECTION]: There are no attempts to override system instructions, bypass safety filters, or implement 'DAN' style role-play. The instructions are focused strictly on data analysis and report formatting.- [REMOTE_CODE_EXECUTION]: The skill uses mathematical logic and trend analysis performed within the agent's context. It does not download external packages, execute shell scripts, or use dynamic code evaluation.- [SAFE]: The skill includes a 'Medical Safety Boundaries' section that provides clear constraints on what the agent should not do, such as diagnosing injuries or prescribing treatments, which is a standard safety practice for health-related applications.
Audit Metadata