bitget-wallet

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The scripts order_make_sign_send.py and social_order_make_sign_send.py utilize importlib.import_module to load the local bitget-wallet-agent-api.py script. This is used to handle the hyphenated filename which is incompatible with standard import statements. While the targets are local, dynamic loading of executable content is a monitored pattern.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the Bitget API (copenapi.bgwapi.io), such as token narratives, social descriptions, and AI-generated market summaries, which are then presented to the agent.
  • Ingestion points: External API responses parsed in scripts/bitget-wallet-agent-api.py.
  • Boundary markers: There are no explicit instructions to wrap these external text fields in delimiters to prevent the agent from following embedded instructions.
  • Capability inventory: The skill has network access via the requests library and file system write access for temporary key management.
  • Sanitization: The skill relies on standard JSON decoding without specific sanitization for natural language instructions embedded within the data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 04:29 AM
Security Audit — agent-trust-hub — bitget-wallet