nansen-limit-orders
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, such as the Nansen API and blockchain records, through commands like
nansen trade limit-order listandnansen wallet show. This data enters the agent's context and could potentially contain malicious content aimed at influencing subsequent agent actions. - Ingestion points: SKILL.md (via CLI outputs from order lists and wallet information)
- Boundary markers: Not present in the provided instructions
- Capability inventory: SKILL.md (execution of nansen CLI commands via Bash tool)
- Sanitization: Not explicitly implemented for the data retrieved from external API/blockchain sources
Audit Metadata