application-review
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to review and analyze untrusted application source code and project configurations.
- Ingestion points: Application codebases, build scripts, and configuration files for various technology stacks (Swift/macOS, Electron, Tauri, JVM) provided by the user.
- Boundary markers: No specific delimiters or instructions to ignore embedded content are provided to protect the agent from malicious instructions that might be hidden in comments or data within the files being reviewed.
- Capability inventory: The skill is intended for use in environments where the agent has access to development tools, file system operations, and shell execution (e.g., xcodebuild, cargo, gradlew, and macOS security tools like spctl).
- Sanitization: No sanitization or escaping of the input source code is required by the instructions.
Audit Metadata