turborepo
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and follow documentation stored within the
node_modulesdirectory (node_modules/turbo/docs/README.md). This creates a path for indirect prompt injection where instructions embedded in these documentation files could influence the agent's actions.\n - Ingestion points: The agent is directed to read and interpret content from
node_modules/turbo/docs/README.mdand related documentation files.\n - Boundary markers: There are no instructions or markers provided to delimit the documentation content or to warn the agent to ignore any embedded commands or instructions.\n
- Capability inventory: The agent is expected to use the information read to modify
turbo.jsonconfigurations, update package scripts, and adjust CI workflows.\n - Sanitization: The skill does not implement any sanitization or validation of the documentation content before it is processed by the agent.\n- [COMMAND_EXECUTION]: The skill provides a utility command (
node -p "require.resolve('turbo/package.json')") to find the installation path of the Turborepo package. This is used solely for locating the relevant documentation files and does not perform any dangerous operations.
Audit Metadata