The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown documentation and configuration files. It does not contain any executable scripts (Python, JavaScript, shell, etc.) or binary files.
[EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install its core functionality and dependencies from external sources.
Evidence: The README.md and SKILL.md files provide npx skills add commands to fetch resources from the InjectiveLabs/agent-skills repository. These resources belong to a trusted vendor.
[INDIRECT_PROMPT_INJECTION]: The skill describes a workflow that processes external data from the Injective blockchain, which creates a theoretical indirect injection surface.
Ingestion points: Data is ingested from the blockchain via tools like account_balances, account_positions, and token_metadata.
Boundary markers: The instructions do not define explicit delimiters to separate blockchain-sourced strings (like token names or symbols) from agent instructions.
Capability inventory: The skill instructs the agent to invoke the subaccount_deposit tool to execute transactions based on the queried data.
Sanitization: There are no specific sanitization steps provided for strings retrieved from the blockchain APIs.

injective-trading-account