swiftui-localize

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONNO_CODE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill analyzes untrusted project data (source code and resource files) and performs refactoring or translation. This creates a surface for indirect prompt injection if malicious instructions are embedded in the analyzed strings.
  • Ingestion points: Project source files (.swift, .m, .strings, .xcstrings) read via Read and Grep tools.
  • Boundary markers: No specific delimiters or warnings to ignore embedded instructions are present in the provided templates or metadata.
  • Capability inventory: Read, Grep, Glob, and Bash (with write access in apply mode).
  • Sanitization: No explicit sanitization or validation of string content is documented in the analyzed configuration.
  • Command Execution (LOW): The skill configuration requests permissions for shell command execution (Bash) and filesystem modification (read_only: false). While necessary for validating resource formats (e.g., via plutil) and applying changes, these capabilities increase the potential impact of any successful prompt injection.
  • No Code (SAFE): The skill consists of documentation, report templates, and metadata without any Python or JavaScript scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:17 PM