skills/samhvw8/dotfiles/research/Gen Agent Trust Hub

research

Pass

Audited by Gen Agent Trust Hub on Jun 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a research methodology involving web and GitHub searches across multiple languages. While fetching external data inherently involves a surface for indirect prompt injection, this is the intended functionality of the skill. No specific malicious instructions or risky configurations were found.
  • Ingestion points: Data is gathered from web sources and GitHub repository information via WebSearch, WebFetch, and the gh CLI (SKILL.md).
  • Boundary markers: The methodology focuses on cross-referencing and mandatory source attribution, which provides functional verification of fetched data.
  • Capability inventory: Tools are used for searching and fetching information, and the skill includes instructions for generating research reports in a local ./report/ directory.
  • Sanitization: Information is cross-referenced across multiple sources and languages to ensure accuracy and minimize the impact of any single potentially untrusted source.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 2, 2026, 05:36 PM
Security Audit — agent-trust-hub — research