us-stock-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and reference templates. It does not include any executable scripts, binary files, or external dependencies, which significantly limits the potential for malicious behavior.
- [INDIRECT_PROMPT_INJECTION]: The analysis workflow relies on gathering data from external websites via web search tools. This creates an ingestion point for untrusted content that could theoretically contain instructions intended to bias the agent's output. However, the skill's capabilities are restricted to text-based reporting, and it lacks tools for file system modification, network exfiltration of local data, or command execution.
- Ingestion points: Market data, news, and financial reports from the web (SKILL.md).
- Boundary markers: None explicitly defined.
- Capability inventory: Text report generation only; no high-privilege tool access.
- Sanitization: Not specified for search result content.
Audit Metadata