The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the hithink-finance command-line utility to perform its functions, specifically using the valuation snapshot, capabilities, and schema commands. These are vendor-provided tools intended for the skill's primary purpose.
[DATA_EXFILTRATION]: The skill facilitates data movement by querying external financial APIs (requiring an API Key) and optionally writing results to the local file system using the --output parameter. This behavior is documented and consistent with the skill's utility for processing financial metrics.
[INDIRECT_PROMPT_INJECTION]: The skill processes data retrieved from an external financial API, which represents an attack surface where malicious content in the data could potentially influence agent behavior.
Ingestion points: The skill ingests data via the hithink-finance valuation snapshot command output (referenced in references/valuation-snapshot.md).
Boundary markers: Instructions are provided to the agent to report only summaries or file paths when dealing with large datasets, which limits the volume of untrusted data directly interpreted by the agent.
Capability inventory: The agent has the capability to execute the hithink-finance CLI and write files to disk via command parameters.
Sanitization: The skill implements input validation by limiting tokens to 100 and performing de-duplication, though it does not explicitly define sanitization for the content of the API response itself.

hithink-finance-valuation