evolve
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill performs automated version checks by fetching version metadata from the author's public GitHub repository and suggests installing additional modular components from established vendor repositories (e.g., miles990/claude-software-skills).
- [REMOTE_CODE_EXECUTION]: While the skill facilitates the installation of external plugins, it explicitly instructs the agent to prompt the user for manual confirmation and terminal execution, avoiding silent or hidden background updates.
- [COMMAND_EXECUTION]: The skill includes utility scripts for project maintenance, such as validating skill manifests and generating plugin metadata, which operate on the local file system using standard bash commands.
- [DATA_EXFILTRATION]: The skill implements a 'Scope Detection' logic designed to identify sensitive information like API keys and tokens, ensuring they are restricted to local project memory and redacted before being used in global contexts.
- [SAFE]: The overall architecture emphasizes security guardrails, including the specific denial of elevated privileges (sudo) and the enforcement of isolated environments for high-risk or experimental development tasks.
Audit Metadata