broker
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides documentation and shell scripts in
references/authentication.mdfor interacting with the KuCoin API usingcurlandopenssl. These tools are used for legitimate authentication and data retrieval from the vendor's API endpoints. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external REST API endpoints, creating a potential surface for instructions to be embedded in API responses.
- Ingestion points: Data is ingested from various KuCoin API endpoints defined in
SKILL.md(e.g.,/api/v2/affiliate/queryInvitees,/api/v2/broker/queryUser). - Boundary markers: The agent is instructed to format output as JSON, providing some structural separation for the results.
- Capability inventory: The skill includes capabilities for network requests via
curland instructions for the agent to read credential files. - Sanitization: There are no explicit instructions for sanitizing or filtering the content of the API responses before the agent processes them.
Audit Metadata