debugging-devtools-extensions
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where the agent prompts the user for a VM Service URI and subsequently uses this input to construct shell commands for opening a web browser (e.g.,
open,xdg-open,start). This pattern creates a potential command injection surface if the agent does not sanitize the user's input before execution. - Ingestion points: The agent collects a VM Service URI from the user (documented in Step 3 and 4).
- Boundary markers: Absent. The instructions do not specify delimiters or safety warnings for the agent when handling this input.
- Capability inventory: The skill utilizes shell execution for
flutter runand system-level browser launch commands (open,xdg-open,start) inSKILL.md. - Sanitization: Absent. There are no instructions provided to validate or escape the user input before it is passed to the shell.
- [COMMAND_EXECUTION]: The skill requires the agent to execute various shell commands to launch Flutter applications and system browsers. While appropriate for the skill's intended use case as a developer tool, these commands operate on the local file system and network environment.
Audit Metadata