feishu-doc-reader

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill manages Feishu API credentials through a local configuration file (./reference/feishu_config.json). It explicitly recommends setting secure file permissions (chmod 600) to protect these secrets and warns against committing them to version control.
  • [EXTERNAL_DOWNLOADS]: The skill makes network requests to open.feishu.cn, which is the official Feishu Open API endpoint, to retrieve document data. This is an expected behavior for the skill's purpose.
  • [COMMAND_EXECUTION]: The skill utilizes local shell and Python scripts for its operations, requiring standard execution permissions (chmod +x) to be set by the user on files distributed with the skill.
  • [PROMPT_INJECTION]: The skill processes untrusted external data from Feishu documents (docx, sheet, bitable, wiki). This creates a potential surface for indirect prompt injection if the retrieved content contains hidden instructions designed to influence the AI agent's behavior. Evidence chain:
  • Ingestion points: API responses from Feishu document endpoints.
  • Boundary markers: None specified in the instructions for separating document content from agent instructions.
  • Capability inventory: The skill can execute local shell commands and Python scripts.
  • Sanitization: Not explicitly documented in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 01:19 AM
Security Audit — agent-trust-hub — feishu-doc-reader