read-feishu-doc

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local shell and Python scripts (e.g., read_doc.sh, get_feishu_doc_blocks.py) to facilitate document extraction. This is standard functionality for the skill's purpose.
  • [DATA_EXFILTRATION]: The skill communicates with the official Feishu API (open.feishu.cn) to retrieve document data. This is a well-known service used for the primary purpose of the skill.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes content from external Feishu documents.
  • Ingestion points: External document content retrieved via scripts/read_feishu_doc.py and scripts/get_feishu_doc_blocks.py.
  • Boundary markers: The skill documentation does not mention explicit markers to delimit external content within the LLM context.
  • Capability inventory: The skill possesses shell and Python execution capabilities for API interaction.
  • Sanitization: The skill claims to perform structured JSON extraction, though specific sanitization logic for the ingested document text is not described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 03:50 PM
Security Audit — agent-trust-hub — read-feishu-doc