deep-research

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill leverages native platform tools (WebSearch/WebFetch) for their intended purpose and implements quality control measures to ensure citations and factual accuracy.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) due to the ingestion of untrusted web content. Evidence: (1) Ingestion points: The skill uses WebSearch and WebFetch tools in SKILL.md to retrieve external data. (2) Boundary markers: No specific delimiters or instructions to ignore embedded prompts are provided in the ResearchScout prompt templates. (3) Capability inventory: The skill is restricted to web research and synthesis tools; no high-risk capabilities like file system modification or code execution are present. (4) Sanitization: No explicit sanitization of fetched content is performed, though the workflow includes a 'validate and triangulate' phase to verify claims across multiple sources. This surface is considered safe given the skill's primary research purpose and lack of dangerous capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 12:35 PM
Security Audit — agent-trust-hub — deep-research