industry-chain
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process information from external financial sources, including news feeds, regulatory filings, and industry reports (e.g., Yahoo News, SEC filings, and various financial data endpoints). This creates a potential surface for indirect prompt injection if an attacker-controlled document or news article contains malicious instructions. However, the skill lacks dangerous capabilities such as arbitrary command execution or file system writes, and it emphasizes strict evidence-based filtering, which limits the potential impact of such an attack.
Audit Metadata