spec-to-repo
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to interpret untrusted natural-language project specifications to scaffold repositories and generate code. This creates a surface where a malicious specification could attempt to trick the agent into generating backdoors or malicious scripts within the new project.
- Ingestion points: User-provided project descriptions, PRDs, or requirements docs (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or boundary markers to isolate the user-provided spec from the agent's internal reasoning or file-generation instructions.
- Capability inventory: The skill uses file-writing capabilities to create the project structure and executes a Python-based validation script (
scripts/validate_project.py) via the shell. - Sanitization: The skill lacks explicit instructions for sanitizing or escaping content from the user spec before it is used to generate file contents.
- [SAFE]: The utility script
scripts/validate_project.pyimplements security best practices by checking for the presence of.envfiles, ensuring that developers do not accidentally commit sensitive credentials during the scaffolding process.
Audit Metadata