vike-cross-venue-perps
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
vikecommand-line tool to fetch funding and spread data for financial analysis. These commands are restricted to the author's provided toolset and align with the intended use case. - [INDIRECT_PROMPT_INJECTION]: The skill processes market data originating from external trading venues. This represents an attack surface where an external source could theoretically provide malicious content, though the risk is minimized by the use of structured data formats.
- Ingestion points: Output from
vike perp fundingandvike perp spreadscommands in SKILL.md. - Boundary markers: The skill specifies the
--jsonflag, requesting structured data which limits the likelihood of plain-text instruction injection. - Capability inventory: The skill is limited to executing the
vikeCLI within the provided environment. - Sanitization: No explicit sanitization logic is provided in the prompt; the agent relies on its internal handling of command output.
Audit Metadata