clinic-patient-retention
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or dangerous commands were detected within the skill instructions.- [DATA_EXPOSURE]: The skill implements proactive privacy safeguards by explicitly instructing the agent to never request, repeat, or process personally identifiable information (PII) like patient names or medical records. It directs the agent to use row numbers or placeholders instead.- [EXTERNAL_DOWNLOADS]: The skill references several external URLs for legal and regulatory compliance (such as official government domains in Spain, the UK, and Australia). These references are relevant to the skill's functionality and target authoritative public records.- [INDIRECT_PROMPT_INJECTION]: While the skill is designed to process user-supplied clinic data, it contains explicit instructions for the agent to treat all user input strictly as data and not as executable instructions, which helps mitigate risks associated with untrusted content.
Audit Metadata