longbridge-technical

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing specialized Python libraries (czsc, smartmoneyconcepts, pandas, numpy) via pip to support its analytical functions.\n- [COMMAND_EXECUTION]: The skill uses the longbridge CLI to interact with market and account data. These commands are vendor-specific and necessary for the skill's operation.\n- [DYNAMIC_EXECUTION]: The skill runs Python code locally to analyze the data fetched by the CLI. It references an external script, scripts/signal_engine.py, for advanced Elliott Wave calculations.\n- [INDIRECT_PROMPT_INJECTION]:\n
  • Ingestion points: Market data in JSON format is fetched via the longbridge CLI across multiple analysis modules.\n
  • Boundary markers: The instructions do not define specific delimiters to prevent the agent from interpreting text within the market data as instructions.\n
  • Capability inventory: The agent can execute shell commands and Python scripts to process the ingested data.\n
  • Sanitization: The Python scripts use basic numeric validation (pd.to_numeric) to process the market data, which offers limited protection against non-numeric injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:20 AM
Security Audit — agent-trust-hub — longbridge-technical