swift-clean-types
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses a direct interpolation pattern for user-provided input without boundary markers or instructions to disregard embedded commands.
- Ingestion points: The
$ARGUMENTSvariable is directly placed into the instruction block inSKILL.md. - Boundary markers: None. The input is not wrapped in delimiters (like XML tags or markdown blocks) that would help the agent distinguish between user data and system instructions.
- Capability inventory: The skill is configured with
Read,Edit,Glob,Grep, andBashtools in its frontmatter, providing significant file system and shell access. - Sanitization: No validation or sanitization is performed on the input to ensure it is a valid file path or code snippet before processing.
Audit Metadata