Cross-Platform Build Expert
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific data which serves as an ingestion point for potentially malicious instructions.
- Ingestion points: The skill parses and validates project files like
tauri.conf.json,Cargo.toml, andentitlements.plistas described inSKILL.mdandreferences/advanced-patterns.md. - Boundary markers: There are no instructions provided to the agent to treat the content of these configuration files as untrusted or to ignore any natural language instructions embedded within them.
- Capability inventory: The skill facilitates the execution of system-level tools including
npm,cargo,signtool,codesign, andnotarytool. It also usesCommand::newin Rust tests to execute shell commands. - Sanitization: The skill does not implement sanitization or validation of configuration values before using them as arguments in command-line build and signing processes.
- [COMMAND_EXECUTION]: The skill facilitates the execution of shell commands and build tools as part of its core functionality.
- It provides instructions and templates for executing build commands (
npm run build), running platform-specific tests, and using security utilities for signature verification. - CI/CD workflow examples include the use of
sudo apt-getto install necessary system dependencies in Linux environments. - [EXTERNAL_DOWNLOADS]: The skill references external resources and configuration from well-known and trusted providers.
- Uses DigiCert's official timestamping service (
http://timestamp.digicert.com) for code signing on Windows. - Incorporates well-known GitHub Actions for CI/CD, such as
actions/checkout,actions/setup-node, andactions/upload-artifact. - References the
dtolnay/rust-toolchainrepository for managing Rust environments, which is a standard and trusted resource in the ecosystem.
Audit Metadata