tradingview-mcp-assistant

Warn

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions direct the user to clone and install code from a remote repository (https://github.com/tradesdontlie/tradingview-mcp.git) and run local shell scripts (scripts/launch_tv_debug_mac.sh, etc.) from that repository. This source is not from a verified or well-known organization.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by ingesting untrusted data from TradingView charts and Pine Script indicators.
  • Ingestion points: Untrusted data enters the agent context via tools such as data_get_study_values, data_get_pine_labels, data_get_pine_tables, and data_get_pine_boxes (SKILL.md).
  • Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the prompt templates for these data sources.
  • Capability inventory: The agent has access to powerful capabilities including writing and compiling Pine Script code (pine_set_source, pine_smart_compile), creating alerts (alert_create), and saving files to the local system (capture_screenshot) (SKILL.md).
  • Sanitization: No sanitization or validation of external chart data is performed before it is processed by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 16, 2026, 03:50 PM
Security Audit — agent-trust-hub — tradingview-mcp-assistant