swiftui-gestures
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided SwiftUI code and interaction plans, which represents an ingestion surface for untrusted data. While there are no specific boundary markers or sanitization instructions provided in the SKILL.md to mitigate prompt injection from this data, the skill does not possess dangerous capabilities (such as network access or file system writes) that could be exploited via this vector, making the risk consistent with the skill's primary purpose.
- Ingestion points: User-supplied SwiftUI interaction plans and code snippets referenced in the evaluation prompts.
- Boundary markers: Absent. There are no instructions for the agent to use delimiters or ignore instructions embedded in the user code.
- Capability inventory: No shell execution, network operations, or sensitive file system access commands are present in the skill.
- Sanitization: Absent. The skill does not instruct the agent to sanitize or validate the content of the user input.
Audit Metadata