semble-setup

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]:
  • The skill downloads the semble package from the official Python Package Index (PyPI) using the uvx tool, which is standard for Python-based utilities.
  • It references the uv tool installation script from astral.sh, which is the established domain for this well-known technology provider.
  • [COMMAND_EXECUTION]:
  • The skill executes a series of shell scripts to manage MCP registration (semble-mcp.sh), track project status (semble-state.sh), and audit codebase coverage (semble-project.sh).
  • System-level mutations, such as installing packages via homebrew, are protected by explicit user confirmation gates using the AskUserQuestion tool.
  • [REMOTE_CODE_EXECUTION]:
  • Automated scanners identified the use of a remote installation script (https://astral.sh/uv/install.sh) piped to shell.
  • Verification confirms this command is only presented as a manual fallback instruction for the user and originates from a trusted, well-known service provider.
  • [SAFE]:
  • The skill implements local telemetry logging to monitor search performance and tool conversion, stored within the project's own .claude/semble/ directory.
  • No evidence of data exfiltration, credential harvesting, or unauthorized privilege escalation was found during the analysis. The skill's behavior aligns entirely with its stated purpose as a developer productivity tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 06:23 PM
Security Audit — agent-trust-hub — semble-setup