The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources within the Feishu platform, which represents a potential attack surface for indirect prompt injection.
Ingestion points: Data enters the agent's context through tools and scripts that retrieve Feishu messages (feishu_api.py), cloud documents (feishu_api.py, SKILL.md), and Bitable records (bitable.py, feishu_api.py).
Boundary markers: No explicit boundary markers or instructions to the agent to treat retrieved data as untrusted are present in the SKILL.md or associated scripts.
Capability inventory: The skill has access to powerful system-level tools including Bash, Read, Write, and Edit, as defined in the allowed-tools section of SKILL.md.
Sanitization: The provided scripts perform standard API interactions but do not include specific sanitization or filtering logic to neutralize potential instructions embedded within the Feishu data before it is processed by the AI agent.

feishu-automation