feishu-fetch-doc
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process content from external Feishu (Lark) documents, converting them into Markdown for the agent to interpret. This introduces a vulnerability surface where data sourced from these documents could contain adversarial instructions.
- Ingestion points: The skill fetches external content from Feishu documents via
doc_idor URLs (e.g.,feishu.cn/docx/,feishu.cn/wiki/) and parses media tokens from the resulting content. - Boundary markers: The skill instructions do not specify any boundary markers or instructions for the agent to ignore embedded commands within the fetched document content.
- Capability inventory: The skill uses associated tools to read docx, sheets, and bitables, and it includes a file download capability (
feishu_doc_media) that can write to a specifiedoutput_path. - Sanitization: There is no evidence of sanitization, filtering, or validation performed on the Markdown content before it is passed to the agent context.
Audit Metadata