news-summarizer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • PROMPT_INJECTION (LOW): Potential for indirect prompt injection due to the ingestion of untrusted external data.
  • Ingestion points: The skill retrieves live news content from external websites using the search_web tool (SKILL.md).
  • Boundary markers: Absent. The prompt does not instruct the agent to use delimiters or ignore instructions embedded within the fetched news articles.
  • Capability inventory: The agent performs web searches, summarizes content, and translates text.
  • Sanitization: No sanitization or validation logic is defined to filter malicious payloads in search results.
  • EXTERNAL_DOWNLOADS (SAFE): The skill targets news sources like Google News for its primary function. While it downloads data, it does not involve the execution of remote scripts or binary files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:21 PM