ios-app-icon-generator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill identifies a surface for indirect prompt injection by interpolating untrusted user data into a generated executable HTML artifact.
- Ingestion points: User input regarding the app's purpose, name, and brand colors (SKILL.md, Process section).
- Boundary markers: Absent.
- Capability inventory: Generates HTML artifacts with embedded SVG and JavaScript for client-side image processing (SKILL.md, Phase 2).
- Sanitization: The skill does not instruct the agent to sanitize or escape user-provided strings before inserting them into the HTML 'title' or 'body' tags, potentially allowing for cross-site scripting (XSS) or structural manipulation within the generated file.
- [REMOTE_CODE_EXECUTION] (SAFE): No patterns of remote script execution or external command invocation were detected.
- [DATA_EXFILTRATION] (SAFE): No access to sensitive local files or network exfiltration patterns identified.
Audit Metadata