apple-appstore-reviewer

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze external repositories, creating a vector where malicious instructions embedded in source code or project metadata could attempt to influence the agent's behavior.
  • Ingestion points: The skill explicitly instructs the agent to locate and inspect project files including Info.plist, *.entitlements, PrivacyInfo.xcprivacy, StoreKit configurations, and general application source code.
  • Boundary markers: There are no explicit instructions to use delimiters or ignore embedded natural language instructions found within the project files.
  • Capability inventory: The skill restricts the agent to observation and reporting; it specifically mandates 'Change no code initially' and 'Do not edit code or propose PRs in the first pass,' which significantly limits the potential impact of an injection.
  • Sanitization: The instructions do not include procedures for sanitizing or escaping content extracted from the analyzed codebase before it is integrated into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 08:39 PM
Security Audit — agent-trust-hub — apple-appstore-reviewer