google-dev-news-linebot
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches news content from several official Google domains, including developers.googleblog.com, blog.google, cloud.google.com, and deepmind.google. These are well-known and trusted sources for technology news.
- [INDIRECT_PROMPT_INJECTION]: The skill processes summaries from external RSS feeds and interpolates them directly into the prompt sent to the Gemini API. While the script performs basic sanitization by stripping HTML tags and truncating the text, it lacks explicit boundary markers or instructions to the model to ignore potential malicious commands embedded in the news text. However, given the skill's primary function is to generate text for the user, the security impact of such an injection is minimal.
Audit Metadata