aiagent-check-setup
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: Executes shell commands to verify installed tool versions (Git, Node.js, npm, Python, etc.) and check for the existence of Git hooks.
- [CREDENTIALS_UNSAFE]: References checking for the existence of .env files and credential stores, but provides a safeguard by instructing the agent not to print or reveal the actual secret values.
- [PROMPT_INJECTION]: The skill reads external documentation and checklist files. This presents a potential surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: docs/codex-safety.md, courses/aiagent/lesson02-setup/ch01-environment/practice/checklist.md
- Boundary markers: Absent; the skill does not use specific delimiters to isolate the content of the documentation files.
- Capability inventory: Version checks for git, node, npm, python3, claude, and cursor; file system read access.
- Sanitization: Absent; the content of the documentation is processed directly to confirm course progress.
Audit Metadata