appstore-review
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONREMOTE_CODE_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project data, which creates a vulnerability surface for indirect prompt injection if malicious instructions are embedded in the files being audited.\n
- Ingestion points: The skill reads local project files (
.swift,Info.plist,PrivacyInfo.xcprivacy), asset catalogs, and metadata. It also instructs the agent to validate external URLs for support and privacy policies.\n - Boundary markers: Absent. The instructions do not define clear delimiters or provide specific warnings to the agent to ignore instructions found within the project data during the audit process.\n
- Capability inventory: The skill relies on file system read access and network capabilities to inspect the project and validate links.\n
- Sanitization: Absent. Project content is ingested and analyzed without explicit sanitization or escaping mechanisms.\n- [REMOTE_CODE_EXECUTION]: The installation process involves cloning a remote repository and executing a shell script.\n
- Source:
https://github.com/3paws-ai/mobile-ai-skills.git(Vendor resource).\n - Execution method:
./scripts/install.sh appstore-review.\n - Context: This is a standard installation procedure for the vendor's tools and originates from the author's official infrastructure.
Audit Metadata