turborepo
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted monorepo configuration data, such as package.json and turbo.json, which creates a surface for indirect prompt injection.
- Ingestion points: The agent reads and analyzes local monorepo files (package.json, turbo.json, and directory structure) to provide tailored guidance.
- Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat content within these files as untrusted or to ignore potentially malicious instructions embedded in fields like script names or task descriptions.
- Capability inventory: The skill assists the agent in generating and modifying shell scripts, CI configurations, and task pipelines, which are execution vectors.
- Sanitization: There is no evidence of sanitization or escaping mechanisms for handling external content before it is processed by the agent or interpolated into suggested configurations.
Audit Metadata