nx-run-tasks
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent on how to execute shell commands using the Nx CLI, including commands such as
nx run,nx run-many, andnx affectedfor tasks like building, testing, and linting. - [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface by directing the agent to interpolate user-provided project names, task names, and flags directly into shell commands.
- Ingestion points: User input is used for the , , and various CLI flags within the commands described in SKILL.md.
- Boundary markers: There are no boundary markers or delimiters specified to protect against malicious commands embedded in user-supplied strings.
- Capability inventory: The agent is given instructions to execute arbitrary subprocesses via the
nxCLI and common package managers likenpxoryarn. - Sanitization: The skill contains no instructions for the agent to sanitize, escape, or validate external input before including it in a command line.
Audit Metadata