external-context

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by design as it fetches and processes arbitrary content from the internet.
  • Ingestion points: Web content retrieved via WebSearch and WebFetch tools used by sub-agents.
  • Boundary markers: Prompt templates for both the Gemini and parallel agent paths lack explicit delimiters or instructions to ignore potentially malicious commands within the fetched web data.
  • Capability inventory: The skill utilizes ask_gemini and Task tools to spawn agents with web access and text synthesis capabilities.
  • Sanitization: No explicit sanitization or filtering of the retrieved external content is performed before it is processed by the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 05:04 AM