apitube-news-api
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill acts as an interface for fetching external news data, creating a surface for indirect prompt injection attacks where malicious instructions could be embedded in the news content.
- Ingestion points: News articles and metadata are retrieved from APITube API endpoints such as /news/everything and /news/article.
- Boundary markers: The documentation does not define specific delimiters or instructions for the agent to distinguish between the fetched news content and its core operational directives.
- Capability inventory: The skill is designed for data retrieval; however, the agent utilizing this data may possess other tools or capabilities that could be influenced by injected instructions.
- Sanitization: No mechanisms for sanitizing, filtering, or validating the integrity of the external news content are described.
Audit Metadata