github-deep-research

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill interacts with the GitHub API (api.github.com) to retrieve repository metadata and content. This is a legitimate function for a research tool and utilizes a well-known service.
  • [COMMAND_EXECUTION]: The workflow executes local Python scripts, github_api.py and md2html.py, which are included in the skill package. These scripts perform data processing and formatting without downloading untrusted code.
  • [PROMPT_INJECTION]: The skill processes data from external repositories and web pages, representing an indirect prompt injection surface. However, the skill focuses on summarizing this information and does not provide a path for the ingested content to execute dangerous commands or access sensitive system data.
  • [SAFE]: No obfuscation, persistence mechanisms, or privilege escalation patterns were detected. The skill maintains security by avoiding hardcoded credentials and using controlled script execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 01:27 AM
Security Audit — agent-trust-hub — github-deep-research