lov-electron-app-relaunch
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted project data (such as process.env, process.argv, and package manager configurations) to determine application restart parameters. This ingestion creates a potential surface where malicious instructions embedded in project files could influence agent behavior.\n
- Ingestion points: SKILL.md Step 1 details the collection of runtime environment variables, startup arguments, and parent process identities.\n
- Boundary markers: The instructions lack explicit directives for the agent to use boundary markers or ignore embedded instructions when parsing this external data.\n
- Capability inventory: The skill utilizes powerful capabilities including spawn for process creation, and runtime-specific APIs (app.relaunch, AppHandle::request_restart) for process control.\n
- Sanitization: While the skill documentation advises removing specific environment variables for performance, it does not prescribe security-focused sanitization for data interpolated into launch commands.\n- [DYNAMIC_EXECUTION]: The core functionality of the skill involves the dynamic assembly and execution of relaunch plans by spawning new processes based on runtime discovery.\n
- Evidence: references/relaunch-contract.md defines the logic for capturing execPath and args from the current environment to launch a successor process, which is an intended use case for lifecycle management tools.
Audit Metadata