turborepo
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input, which constitutes an indirect prompt injection surface.\n
- Ingestion points: User data enters the agent context via the $ARGUMENTS variable in command/turborepo.md.\n
- Boundary markers: The skill uses tags to separate user input from system instructions.\n
- Capability inventory: The skill empowers the agent to modify build configurations (turbo.json) and manage workspace dependencies across the monorepo, which are sensitive operations.\n
- Sanitization: No specific input sanitization or validation protocols are defined for the processed user arguments.
Audit Metadata