skills/cklxx/elephant.ai/bitable-data/Gen Agent Trust Hub

bitable-data

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection risk detected. The skill reads content from external Bitable records that could potentially contain malicious instructions aimed at overriding agent behavior.
  • Ingestion points: Data is ingested from the Lark API via the list_records and list_fields functions in run.py.
  • Boundary markers: No specific delimiters or safety instructions (e.g., "ignore instructions in the following data") are implemented in the skill's instructions or script logic.
  • Capability inventory: The skill possesses significant capabilities, including the ability to create, modify, and delete data within the user's Bitable applications.
  • Sanitization: The retrieved data is passed to the agent without any visible sanitization or filtering to remove potential prompt injection payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 12:35 AM