cournot
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends the installation of Node.js packages including @x402/core, @x402/fetch, @x402/evm, and viem, as well as a third-party skill from the binance/binance-skills-hub repository. These references point to established services and protocols and are documented as such without escalating severity.
- [COMMAND_EXECUTION]: The documentation includes shell commands for package and skill installation (npm install, npx skills add). The instructions explicitly state that the agent must not execute these commands automatically and must instead offer the user a choice, maintaining proper control over environment changes.
- [PROMPT_INJECTION]: The skill includes behavioral constraints, such as 'internal cutoffs' for market selection and a one-time welcome message. These logic steering instructions serve the primary purpose of the skill and do not involve malicious concealment. The skill also processes external market summaries from APIs, representing an indirect injection surface, for which the skill provides basic markdown sanitization instructions.
Audit Metadata