app-store-connect-cli
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is centered around executing shell commands using the
ascCLI tool and the Homebrew package manager. - [EXTERNAL_DOWNLOADS]: The skill instructions involve downloading and installing code from a third-party Homebrew tap (
rudrankriyam/tap) to obtain theascCLI tool. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of customer reviews via the
asc reviewscommand, which introduces a potential surface for indirect prompt injection. - Ingestion points: The
asc reviews --app "123456789"command inreferences/quick-reference.mdfetches content from the App Store. - Boundary markers: No delimiters or protective instructions are provided to help the agent distinguish between data and potential commands within review text.
- Capability inventory: The skill can perform sensitive operations including build uploads (
asc builds upload), device registration (asc devices register), and review responses (asc reviews respond). - Sanitization: There is no evidence of sanitization or filtering applied to the review data before it enters the agent's context.
Audit Metadata