start-building-for-startups
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill is designed to automatically scan the project's codebase, including configuration files (e.g., package.json, pyproject.toml), documentation, and source code. This data is used to inform architectural recommendations and implementation. This behavior creates a potential surface for indirect prompt injection if the ingested project files contain instructions designed to influence the agent's behavior.
- Ingestion points: Automated scanning of source code, configuration files, and README documentation as described in the codebase analysis section.
- Boundary markers: The instructions do not specify the use of delimiters or explicit warnings to the agent to ignore instructions embedded within the scanned codebase.
- Capability inventory: The skill possesses the capability to write new code, generate Infrastructure as Code (Terraform), and modify existing files in the project directory.
- Sanitization: No explicit sanitization or validation of codebase content is mentioned before it is processed by the agent to determine implementation steps.
Audit Metadata