skills/thelobbi/claude/github-agents/Gen Agent Trust Hub

github-agents

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the github/gh-aw CLI extension using gh extension install. The download targets the official GitHub organization, which is a well-known and trusted service.
  • [COMMAND_EXECUTION]: The skill documents the use of GitHub-specific CLI commands (gh aw) and MCP tools for issue and pull request management. These are standard operations for interacting with GitHub's agentic ecosystem.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies that GitHub agents process untrusted data from issue descriptions, PR diffs, and repository configuration files (AGENTS.md). It provides defensive guidance, such as defining clear acceptance criteria, using 'safe outputs' to sanitize agent actions, and maintaining read-only defaults to mitigate risks associated with processing external content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 10:14 AM
Security Audit — agent-trust-hub — github-agents