feishu-doc

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface identified in the skill's documented behavior.
  • Ingestion points: The skill fetches content from external Feishu/Lark sources (Wiki, Docs, Sheets, Bitable) via the 'read' action.
  • Boundary markers: No delimiters or safety instructions are specified to separate external content from system instructions.
  • Capability inventory: The skill possesses extensive write capabilities, including creating, overwriting, appending content, and managing blocks.
  • Sanitization: Documentation does not mention sanitization or validation of the fetched data.
  • [COMMAND_EXECUTION]: The documentation specifies using 'node index.js' to run the skill, which involves executing local JavaScript.
  • [NO_CODE]: No executable source code (e.g., 'index.js') or dependency manifests (e.g., 'package.json') were provided for analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 02:09 PM