nemo-relay-install
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches installation scripts from the official NVIDIA repository on GitHub.
- [REMOTE_CODE_EXECUTION]: Downloaded scripts are executed to install the CLI tool; risk is mitigated by instructions requiring the agent to show the script content to the user for review before execution.
- [COMMAND_EXECUTION]: The skill executes various commands using package managers to install and verify dependencies across multiple environments.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of local project files. Ingestion points: Reads package.json, pyproject.toml, and Cargo.toml from the user's workspace. Boundary markers: Lacks explicit delimiters when interpolating data from these files into its decision logic. Capability inventory: Has the ability to execute shell commands and modify project configurations. Sanitization: No evidence of sanitization or validation of the data extracted from the project manifest files.
Audit Metadata