etherscan
Warn
Audited by Snyk on Feb 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch untrusted public data from Etherscan-compatible APIs (e.g., the getabi and getsourcecode endpoints) and to parse that ABI/source to drive read_contract/write_contract actions (Workflow: Dynamic Contract Interaction), so third-party content can directly influence agent behavior.
Audit Metadata