tradingview-quantitative
Warn
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: MEDIUMREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill instructs the agent and user to execute an external NPM package (@ivotoby/openapi-mcp-server) using the npx command for local API integration. Since the package is hosted on a public registry and authored by an unverified third party (not a trusted vendor), this represents a risk of remote code execution if the package were to be compromised or contain malicious code. Evidence: Found in SKILL.md and references/api-documentation.md (e.g., npx -y @ivotoby/openapi-mcp-server).
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize untrusted external data from sources such as financial news and community trading ideas. These platforms allow user-generated content, which could be used to inject malicious instructions into the agent's context. The skill lacks instructions for the agent to sanitize this data or ignore embedded commands.
- Ingestion points: tradingview_get_news, tradingview_get_news_detail, tradingview_get_ideas_hot, tradingview_get_minds, and tradingview_get_idea_detail (referenced in SKILL.md, references/community-sentiment.md, references/news-briefing.md, and references/event-analysis.md).
- Boundary markers: Not present; the agent is simply instructed to process the data.
- Capability inventory: High-privilege market data retrieval tools, news access, and technical analysis tools.
- Sanitization: None; there are no instructions to validate or filter the content retrieved from external tools.
Audit Metadata