create-project
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute directory creation via 'mkdir -p'. This operation is preceded by a sanitization step that converts input to kebab-case and removes special characters, which significantly reduces the risk of arbitrary command injection.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface.
- Ingestion points: The skill reads from 'projects/PROJECT_INDEX.md' to check for existing projects.
- Boundary markers: There are no explicit delimiters or instructions to ignore instructions embedded within the index file.
- Capability inventory: The skill has access to Read, Write, and Bash tools, allowing it to modify the file system and execute shell commands.
- Sanitization: While Step 1 sanitizes user-provided arguments, there is no explicit validation for the data read from the existing index file.
Audit Metadata