feishu-sheet

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a local Python CLI script (sheet_ctl.py) to process commands. This is standard implementation for agent skills.- [EXTERNAL_DOWNLOADS]: The script communicates with Feishu Open API endpoints to fetch and update spreadsheet data. These are well-known service domains required for the skill's stated purpose.- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to data ingestion from spreadsheets.
  • Ingestion points: Spreadsheet cell content, sheet titles, and metadata are read into the agent context via cmd_read, cmd_info, and cmd_sheets.
  • Boundary markers: No explicit delimiters are used in the output to separate data from instructions.
  • Capability inventory: The skill provides write access to Feishu Spreadsheets via cmd_write.
  • Sanitization: Data retrieved from cells is converted to strings for display without filtering for embedded instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 06:31 AM