Financial Data Fetcher
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted financial news data which serves as a potential vector for indirect prompt injection attacks.
- Ingestion points: The
get_latest_newstool inSKILL.mdfetches headlines, summaries, and URLs from external financial news sources. - Boundary markers: The provided documentation does not specify the use of delimiters or instructions to ignore embedded commands within the fetched news data.
- Capability inventory: The skill is intended for use by AI trading agents to make financial decisions, creating a high-impact target if the agent is manipulated by injected content.
- Sanitization: There is no evidence of content sanitization, filtering, or validation for the external news summaries before they are presented to the agent's context.
Audit Metadata