The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill mentions a third-party Python library tianyancha as an example for programmatic access.
[INDIRECT_PROMPT_INJECTION]: The skill fetches data from external business databases, representing a potential surface for indirect prompt injection if the source data contains malicious instructions.
Ingestion points: API responses from open.api.tianyancha.com and api.qichacha.com (referenced in SKILL.md).
Boundary markers: None present in the documentation examples.
Capability inventory: The skill demonstrates using curl and Python to process external data.
Sanitization: No explicit validation or sanitization of API response content is described.

tianyancha-cn