The Agent Skills Directory

SAFE (SAFE): The project initialization script scripts/create-project.py implements secure coding practices, including strict input validation using regular expressions for project names and IDs. It uses pathlib for file system operations, which effectively prevents directory traversal attacks. No remote dependencies, network operations, or hardcoded credentials were found.- Indirect Prompt Injection (SAFE): While references/project-types.md defines an 'AI Research Checklist' that directs the agent to scan codebase files for dependencies, this behavior is a core functional requirement of the skill and does not include instructions to execute or trust external content blindly. The ingestion of untrusted data is mitigated by the agent's internal safety protocols and the script's name sanitization.

create-project