aso-appstore-screenshots
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts (
compose.py,showcase.py) and the macOSsipsutility via theBashtool to perform image manipulation tasks such as composition, cropping, and resizing to specific App Store dimensions. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests and processes untrusted data from the user's codebase.
- Ingestion points: During the 'Benefit Discovery' phase, the skill reads UI files, data models, READMEs, and metadata files from the local repository.
- Boundary markers: No explicit delimiters or instructions are used to separate or ignore potential instructions embedded within the analyzed code files.
- Capability inventory: The skill can read/write local files, execute shell commands, and invoke image generation tools via the Gemini MCP server.
- Sanitization: No sanitization or validation of the ingested codebase content is specified in the instructions.
Audit Metadata