magpie-setup

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads framework snapshots and dependencies from official Apache Software Foundation sources, including the apache/magpie and apache/comdev GitHub repositories, as well as ASF distribution servers for signed releases.
  • [REMOTE_CODE_EXECUTION]: Executes internal scripts and tools (e.g., permission-audit and agent-guard.py) from the downloaded framework snapshot using Python and uv run.
  • [COMMAND_EXECUTION]: Manages project structure through various system commands, including symlink creation (ln -s), file system operations (cp, rm, mkdir), and the installation of a git post-checkout hook.
  • [DATA_EXFILTRATION]: Ingests repository metadata (such as issue and pull request counts/dates) via the gh CLI to provide 'fit signal' recommendations for skill family selection. The skill explicitly instructs the agent to treat this data as non-executable input.
  • [PROMPT_INJECTION]: Supports 'agentic overrides' where instructions in .apache-magpie-overrides/*.md files are read at runtime to customize framework skill behavior. The skill also implements a self-update mechanism that reloads its own instructions in-flight after updating its committed source code.
  • [SAFE]: The skill utilizes platform capabilities (capability:platform) to perform legitimate configuration management tasks, such as updating sandbox allow-lists in .claude/settings.local.json with user confirmation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 04:21 AM
Security Audit — agent-trust-hub — magpie-setup