nx-plugins
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHPROMPT_INJECTIONCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
- PROMPT_INJECTION (HIGH): The skill is susceptible to indirect prompt injection as it passes user-influenced strings directly into system commands without validation. 1. Ingestion points: The
<plugin>parameter in thepnpm nx addcommand. 2. Boundary markers: Absent; no instructions are provided to the agent to delimit or ignore instructions within the input. 3. Capability inventory: Execution ofpnpm nx listandpnpm nx add, with the latter performing package installation and potentially running lifecycle scripts. 4. Sanitization: Absent; there is no whitelist or validation of the plugin name. - COMMAND_EXECUTION (HIGH): The skill grants the agent the capability to execute arbitrary shell commands on the host system, which could be abused to access sensitive files or modify the environment.
- REMOTE_CODE_EXECUTION (HIGH): The use of
pnpm nx addtriggers the download and execution of external packages from the npm registry, providing a path for remote code execution if a malicious or compromised package is specified.
Recommendations
- AI detected serious security threats
Audit Metadata