ai-news-fetcher

Warn

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (MEDIUM): The skill ingests untrusted data from the public internet via the Tavily MCP tool, which can be manipulated by third parties to include malicious instructions.
  • Ingestion points: Web search results and news content fetched via Tavily.
  • Boundary markers: None specified; there are no instructions to the agent to treat fetched content as data rather than instructions.
  • Capability inventory: The agent is instructed to generate bilingual markdown articles, meaning the untrusted data directly influences the agent's writing and reasoning output.
  • Sanitization: No sanitization, filtering, or validation of the fetched web content is mentioned or implemented in the skill metadata.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 06:40 AM