news-summary

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: Performs network requests via curl to retrieve RSS feeds from well-known news outlets including BBC, Reuters, NPR, and Al Jazeera. These are established services and the behavior is consistent with the skill's purpose.
  • [DATA_EXFILTRATION]: Communicates with the OpenAI API to convert text summaries into audio. It correctly handles credentials by referencing an environment variable ($OPENAI_API_KEY).
  • [COMMAND_EXECUTION]: Employs standard command-line tools such as grep and sed to extract titles and descriptions from XML news feeds.
  • [PROMPT_INJECTION]: Ingests external data from news feeds. The skill implements basic sanitization by stripping XML tags before the content is summarized by the AI. This is a standard indirect prompt injection surface for news aggregation tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 07:46 PM
Security Audit — agent-trust-hub — news-summary