swift-coding-guideline
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to read and process external project files and reference documentation, which serves as a potential vector for indirect prompt injection attacks.
- Ingestion points: The agent ingests content from the
references/directory and existing project structure files such asproject.pbxproj,Package.swift, and various Swift source files. - Boundary markers: The instructions do not specify any delimiters or protective prompts to help the agent distinguish between its core instructions and potentially malicious instructions embedded in the processed data.
- Capability inventory: The skill empowers the agent to perform sensitive file system operations, including structural modifications to Xcode project files and source code generation.
- Sanitization: The skill contains no requirements for the agent to validate or sanitize the content it reads from external sources before incorporating it into its decision-making or file-writing processes.
Audit Metadata