skills/craftos-dev/craftbot/github/Gen Agent Trust Hub

github

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for using the official GitHub CLI (gh) to check pull request status, list workflow runs, and query the GitHub API. These operations are standard developer tasks and are appropriate for the skill's purpose.
  • [DATA_EXFILTRATION]: No patterns for accessing sensitive files or exfiltrating credentials were found. All network activity is conducted through the legitimate GitHub CLI tool interacting with GitHub's official API.
  • [PROMPT_INJECTION]: No instructions were found that attempt to override the agent's system prompt or bypass safety guidelines. The skill interacts with external data (GitHub issues and PRs), creating a surface for indirect prompt injection, but the data is used exclusively for display and filtering via jq.
  • Ingestion points: GitHub issue lists and API responses (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: Execution of gh CLI commands for repository interaction.
  • Sanitization: Not explicitly defined in instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 12:15 AM
Security Audit — agent-trust-hub — github