swift-ios
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and modify Swift source code and interpret user requests within a development environment. This creates an ingestion surface where malicious instructions could be embedded in codebase files or user prompts to influence agent behavior.
- Ingestion points: Reads Swift source files, project configuration files (.pbxproj, Package.swift), and user-supplied task descriptions.
- Boundary markers: Not explicitly defined for external content, though the skill provides structured checklists for correctness.
- Capability inventory: Includes file system modification (Edit, Write) and shell command execution (Bash for build and version control tools).
- Sanitization: No specific sanitization or filtering of external data content is mentioned.
Audit Metadata