skills/kirkchen/beat/setup/Gen Agent Trust Hub

setup

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill refers the user to a plugin repository hosted on GitHub (github.com/obra/superpowers). GitHub is a well-known and trusted service for software distribution.
  • [COMMAND_EXECUTION]: The skill utilizes standard shell commands (mkdir -p) to create the necessary directory structure for its operations within the project root. These actions are transparent and necessary for the stated purpose of initializing a project configuration.
  • [INDIRECT_PROMPT_INJECTION]: The skill contains logic to scan local project manifest files (e.g., package.json, go.mod, Cargo.toml) to detect the tech stack.
  • Ingestion points: Tech stack detection occurs by reading common manifest and configuration files in the project root.
  • Boundary markers: The instructions do not define explicit delimiters for file content parsing.
  • Capability inventory: The skill has the ability to write a YAML configuration file and create directories.
  • Sanitization: The skill explicitly mandates validation of the generated configuration against a predefined schema (references/config-schema.md) before writing to disk.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 04:34 AM
Security Audit — agent-trust-hub — setup