Skills
Navigate
skills/calionauta/agent-sync-public/stelow-product-execution-critique/Gen Agent Trust Hub

stelow-product-execution-critique

Fail

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and requires the installation of multiple third-party tools and packages from external repositories. This includes @earendil-works/pi-agent-browser, @juicesharp/rpiv-ask-user-question, nicobailon/pi-intercom, and cursor/plugins.
  • [REMOTE_CODE_EXECUTION]: The skill uses npx and pi install to fetch and execute code from remote registries and GitHub repositories. Examples include running npx -y @earendil-works/pi-agent-browser and installing plugins via pi install git:github.com/cursor/plugins.
  • [COMMAND_EXECUTION]: The skill performs extensive command execution using git, node, python3, and specialized tools like sem, cymbal, and plannotator to analyze the environment and update project files like stelow.json.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its ability to ingest and process data from external sources, such as codebase directories and live URLs. If these sources contain malicious instructions, the agent's auditing logic and decision-making could be compromised.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jul 18, 2026, 10:49 AM
Security Audit — agent-trust-hub — stelow-product-execution-critique