feishu-cli-toolkit

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the Bash tool to execute feishu-cli commands for interacting with Feishu APIs. It also provides complex shell scripts, particularly in the 'Document Attachments Download' section, which use utilities like grep, sed, and tr to process local files.
  • [EXTERNAL_DOWNLOADS]: The skill features multiple commands for downloading content from Feishu (a well-known service), including file download, media download, and wiki export. These operations are consistent with the skill's primary purpose of file and document management.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection by ingesting and processing data from external Feishu sources such as documents, spreadsheets, and wiki pages.
  • Ingestion points: Data enters the context through feishu-cli doc export, wiki get, and sheet read operations.
  • Boundary markers: No explicit boundary markers or 'ignore' instructions are used when processing the exported content in the provided scripts.
  • Capability inventory: The skill can execute system commands via the Bash tool and perform network operations through the feishu-cli utility.
  • Sanitization: The provided processing scripts use regex-based pattern matching (via grep) to extract tokens but do not perform security-focused sanitization of the document content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 08:55 AM