asc-app-shots
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
ascCLI andjqutility to orchestrate App Store Connect operations, including metadata retrieval and asset generation.- [PROMPT_INJECTION]: The skill incorporates external app metadata (name, subtitle, description) into the image generation prompts for Gemini, creating an indirect prompt injection surface. - Ingestion points: Metadata is fetched from App Store Connect via
asccommands as defined inSKILL.md. - Boundary markers: No delimiters or instructions are used to separate external text from prompt instructions in the ScreenPlan templates.
- Capability inventory: The skill performs shell execution, file system writes, and interacts with external image generation APIs.
- Sanitization: External text is summarized but not escaped or validated before being interpolated into prompts.- [EXTERNAL_DOWNLOADS]: The generated HTML output references the
html-to-imagelibrary from a public CDN to provide client-side PNG export capabilities.- [EXTERNAL_DOWNLOADS]: The use ofswift run ascas a fallback execution method may involve the resolution and download of external Swift dependencies at runtime.
Audit Metadata