stelow-product-interface-alternatives

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and provides instructions for installing several external utilities from GitHub and NPM, including cursor/plugins, Prinova/pi-agent-codebase-workflows, and @earendil-works/pi-agent-browser. These tools are documented as standard extensions for the target agent environment.
  • [COMMAND_EXECUTION]: The skill utilizes shell commands (bash, awk, grep) and inline node scripts to manage the workflow. These operations include reading the stelow.json configuration, implementing file-level locks to prevent parallel write conflicts, and formatting design proposals. All operations are confined to the project directory and its .stelow metadata folder.
  • [PROMPT_INJECTION]: No malicious prompt injection patterns were found. The instructions provided to sub-agents (workers) are focused on the design task and include requirements for following specific rulesets and output formats.
  • [DATA_EXFILTRATION]: No unauthorized data exfiltration patterns were detected. Network access is restricted to legitimate tool purposes, such as browser-based UI verification via the agent-browser tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 10:48 AM
Security Audit — agent-trust-hub — stelow-product-interface-alternatives