github-researcher

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • External API Interaction: The skill communicates with the official GitHub REST API (api.github.com) to retrieve issue metadata. This is a standard operation for a repository research tool and utilizes the platform's networking capabilities to access public data.
  • Indirect Prompt Injection Surface: The script fetch_issues.py retrieves content (titles and descriptions) from external GitHub issues. Because this content is authored by third parties, it presents a surface for indirect prompt injection where external text could potentially influence the agent's behavior. The skill includes a character truncation mechanism as a basic data handling measure.
  • Workspace Exploration: The instructions guide the agent to use standard system commands like find and curl to explore the project structure and gather specific issue details, which is consistent with its role as a research tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 06:45 AM
Security Audit — agent-trust-hub — github-researcher