nvr-workspace

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes system commands such as pwd, git, and nvr to collect environment metadata. It also invokes a local script, nvr-discover, to identify active Neovim instances. These operations are essential for the skill's stated purpose of workspace discovery.
  • [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by processing data from the local environment without sanitization. * Ingestion points: Data is captured from the filesystem (pwd) and version control (git branch) and directly included in the agent's context. * Boundary markers: No delimiters or protective instructions are used to separate environment data from system instructions. * Capability inventory: The skill is authorized to use the Bash tool, which provides extensive system interaction capabilities. * Sanitization: There is no validation or escaping of environment strings, allowing potential instructions embedded in paths or branch names to be interpreted by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 11:04 PM