tutor-research

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill does not exhibit any malicious patterns. It explicitly implements safety-oriented workflows such as source verification and prioritizing official documentation (context7) over potentially untrusted web content.
  • [PROMPT_INJECTION]: The skill processes external data via web search and fetch tools, which represents a surface for indirect prompt injection. However, the instructions include proactive mitigation strategies such as cross-validating sources and requiring URL verification before inclusion in the final output.
  • Ingestion points: WebSearch, WebFetch, and context7 MCP tools.
  • Boundary markers: While not using specific delimiters, the workflow mandates the creation of a structured markdown output with a mandatory 'Sources' section.
  • Capability inventory: The skill can read local project code using the Agent(Explore) capability to provide contextual research.
  • Sanitization: Includes specific logic for handling conflicting information (prioritizing official docs) and verifying the existence of URLs to prevent hallucinated or malicious links.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 06:27 AM
Security Audit — agent-trust-hub — tutor-research