project-scaffolder
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill takes untrusted user input to determine project stacks and names, which it then uses to generate a complete directory structure and initial code files.
- Ingestion points: The skill workflow in
SKILL.md(Step 1) requires the agent to ask the user to specify project details or infer them from context. - Boundary markers: No specific delimiters or instructions are provided to the agent to treat user-provided project specifications as data only or to ignore instructions embedded within those specifications.
- Capability inventory: The skill possesses the capability to create complex directory structures and write multiple files to the local file system (Workflow Steps 3, 4, and 5).
- Sanitization: There are no instructions for sanitizing or validating user-provided inputs before using them in file creation or configuration generation.
Audit Metadata