persona-health-butler
Fail
Audited by Snyk on Nov 4, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill prompt explicitly instructs the agent to ask the user for or handle secret values (such as an ACN API key and a wallet private key) and pass them as command-line arguments (
--acn-api-key <YOUR_ACN_API_KEY> --private-key <WALLET_PRIVATE_KEY>), creating a serious credential exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow uses
WebFetchto look up nutrition facts and health information from arbitrary URLs, allowing ingestion of outsider-authored web content.
Issues (2)
W007
HIGHInsecure credential handling detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata