newsapi-search
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection because it fetches and processes third-party data from the NewsAPI service.
- Ingestion points: News article titles, descriptions, and content are fetched from
https://newsapi.org/v2/everythingandhttps://newsapi.org/v2/top-headlinesviascripts/search.js. - Boundary markers: The skill does not implement boundary markers or instructions to the agent to ignore embedded commands within the fetched news data.
- Capability inventory: The skill includes file system read access (to
.envfiles for configuration) and outbound network access to the NewsAPI domain. It does not possess arbitrary command execution or file-write capabilities. - Sanitization: There is no sanitization or filtering of the retrieved article content to prevent the inclusion of malicious prompts before the data is returned to the agent context.
Audit Metadata