nansen-polymarket-insider-scan
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external blockchain markets which could theoretically contain malicious instructions embedded in metadata.
- Ingestion points: Market question text, market names, and wallet labels retrieved via
nansen researchcommands are interpolated into the workflow. - Boundary markers: No specific boundary markers or instructions are provided to the agent to treat external strings as untrusted data.
- Capability inventory: The skill possesses the ability to execute Nansen CLI commands via the
Bash(nansen:*)tool to fetch further data. - Sanitization: The skill does not explicitly sanitize or escape the market questions or entity labels before they are processed by the agent.
Audit Metadata