The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill relies on the @sjunepark/ytm Node.js package and a standalone CLI binary hosted on GitHub Releases. These external resources are required for the skill to function but come from a source not recognized as a trusted organization or well-known service.
[COMMAND_EXECUTION]: The skill instructions direct the agent to execute a binary (ytm or bun run cli --) that is installed from external sources to process and format bond yield data.
[INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection by ingesting and processing yield data from external KIS-NET sources.
Ingestion points: Data enters the agent's context through the output of the ytm CLI and the YtmClient.matrix() method.
Boundary markers: The instructions do not specify any delimiters or warnings to ignore instructions that might be embedded in the retrieved financial data.
Capability inventory: The skill's primary capability is formatting and reporting financial data to the user.
Sanitization: The skill performs basic sanitization by converting specific source indicators (like '-') into null values, but does not perform comprehensive validation against malicious prompt content embedded in data strings.

kisnet-ytm