skills/shipshitdev/library/gh-inbox/Gen Agent Trust Hub

gh-inbox

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides standard functionality for GitHub account management. It does not contain any obfuscated code, hardcoded credentials, or unauthorized network communications.\n- [COMMAND_EXECUTION]: The bundled script gh-inbox-report.mjs executes the official GitHub CLI (gh). It uses the execFileSync method with arguments passed as an array, which is a secure implementation that prevents shell command injection.\n- [PROMPT_INJECTION]: While the skill ingests external data (GitHub issue titles and metadata), it explicitly requires the agent to obtain user confirmation before performing any write operations, such as labeling or commenting, which mitigates the risk of unauthorized state changes.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 01:13 PM
Security Audit — agent-trust-hub — gh-inbox