app-store-compliance
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data (mobile app source code, manifests, and store metadata), which presents a potential surface for indirect prompt injection attacks where malicious code could attempt to manipulate the agent's final report.
- Ingestion points: Files within the user-provided artifact such as Info.plist, AndroidManifest.xml, and source repository files are read using tools like
rgandfdas specified inreferences/code-review-checklist.md. - Boundary markers: The instructions do not implement specific delimiters or 'ignore' instructions for the content being analyzed.
- Capability inventory: The skill utilizes local search commands (
rg,fd) and file writing capabilities to generate a compliance report. - Sanitization: There is no evidence of sanitization or escaping of the ingested file content before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill provides the agent with specific shell commands to search the project directory for privacy-sensitive patterns.
- Evidence:
references/code-review-checklist.mdcontains commands such asrg -n --glob '*.plist' 'NS[A-Za-z]+UsageDescription...'andfd -H 'PrivacyInfo.xcprivacy'. These are used for static analysis and are restricted to searching the provided codebase.
Audit Metadata