jww-swift-style
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external Swift source code and project-specific AGENTS.md files, which serves as a data ingestion point for potential indirect prompt injection.
- Ingestion points: Swift source files (**/*.swift) and AGENTS.md files as described in SKILL.md.
- Boundary markers: The instructions do not specify any markers or delimiters to isolate untrusted code from the agent's instructions.
- Capability inventory: The skill is designed to perform source code edits and execute local linting and build commands as specified in SKILL.md.
- Sanitization: No specific filtering or sanitization protocols for external code content are defined.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute repository-specific lint and build commands for verification. This is a common functional requirement for developer tooling and does not involve unusual or high-privilege operations.
Audit Metadata