The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and displays content from Feishu Bitable records which could contain malicious instructions.
Ingestion points: Records are fetched from Feishu Bitable in scripts/bitable_ctl.py via the record list and record get commands.
Boundary markers: The output does not use specific delimiters or warnings to separate data from instructions.
Capability inventory: The skill allows creating, updating, and deleting records and tables in Feishu via api.post, api.put, and api.delete calls.
Sanitization: Content fetched from the API is displayed directly without sanitization or escaping.

feishu-bitable