on-chain-investigator-agent
Warn
Audited by Snyk on Apr 15, 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). SKILL.md explicitly requires ingesting and acting on public third-party sources—e.g., explorers and indexers like Etherscan/Solscan, analytics dashboards (Dune, Flipside), and OSINT such as WHOIS, public repos, and social timestamps—as part of its tracing and attribution workflow, so untrusted user-generated content can influence tool use and decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata