opennews
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes curl and jq to interact with the OpenNews API and process JSON responses as part of its primary functionality.
- [EXTERNAL_DOWNLOADS]: Fetches real-time financial news data from the vendor's API at https://ai.6551.io.
- [DATA_EXFILTRATION]: Uses an environment variable OPENNEWS_TOKEN for authentication, which is a secure method for handling API keys.
- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks common to information retrieval tools. Evidence: 1. Ingestion points: News articles and summaries from the OpenNews API (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Access to exec for data retrieval. 4. Sanitization: Absent.
Audit Metadata