stock-trader-pro
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional markdown files and templates that do not contain malicious commands, network exfiltration patterns, or credential theft vectors. The functionality is focused on providing investment analysis logic through natural language.
- [NO_CODE]: No Python, Node.js, or shell scripts are present in the skill package, which eliminates risks associated with remote code execution or script-based privilege escalation.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted news and market data, creating a potential surface for indirect prompt injection. Ingestion points: Data enters through user-supplied stock tickers and news summaries in SKILL.md and templates/prompt-main.md. Boundary markers: The instructions utilize markdown headers and structured templates but do not include explicit instructions for the model to ignore potential commands within external data. Capability inventory: The skill's capabilities are limited to reading provided templates and generating markdown reports; it lacks access to network tools, shell execution, or sensitive local files. Sanitization: No input sanitization or validation logic is defined for the external news content.
Audit Metadata