nvim-context
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill is designed to execute a specific CLI tool,
nvim-context, via Bash to retrieve editor state. This is a functional requirement of the skill but involves subprocess execution. - [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface. The skill ingests untrusted data from the user's active Neovim session (visual selections and LSP diagnostics). Malicious instructions contained within the code or diagnostics being analyzed could potentially influence the agent's behavior.
- Ingestion points: The
selectionanddiagnosticsfields returned by thenvim-contexttool. - Boundary markers: Not specified in the skill definition.
- Capability inventory: Shell command execution (
nvim-context). - Sanitization: No explicit sanitization or filtering of the ingested editor content is mentioned.
Audit Metadata