agent-config-setup

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to run npx create-agent-config, which fetches and executes the create-agent-config package from the public npm registry.
  • [COMMAND_EXECUTION]: The skill facilitates the execution of shell commands (npm create, npx) to perform system-level operations such as project scanning and file generation.
  • [PROMPT_INJECTION]: The skill acts as a surface for indirect prompt injection (Category 8) because it processes untrusted local files to generate instructions for other AI agents.
  • Ingestion points: The tool scans project-specific files including package.json, tsconfig, and Dockerfile (as described in SKILL.md).
  • Boundary markers: No specific delimiters or instructions to disregard embedded instructions within the project files are mentioned.
  • Capability inventory: The skill is designed to write multiple configuration files (.cursor/rules/*.mdc, CLAUDE.md, AGENTS.md, etc.) across the project directory.
  • Sanitization: There is no evidence of sanitization or validation of data extracted from the project files before it is included in the generated agent configurations.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 10:40 PM