sentry-cocoa-sdk

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the official sentry-wizard tool from the vendor's Homebrew tap (getsentry/tools). This is a standard initialization utility provided by Sentry for automated project configuration.
  • [COMMAND_EXECUTION]: The skill utilizes local shell commands including grep, ls, and cat to perform project discovery. These commands are used to identify existing dependencies, UI frameworks (SwiftUI vs UIKit), and targeted platforms to provide accurate setup recommendations.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it ingests data from the local project environment to tailor its instructions.
  • Ingestion points: Local project configuration files such as Package.swift, Podfile, and .swift source files are read using grep and cat.
  • Boundary markers: The skill does not employ specific delimiters or instructions to ignore potential injection patterns within the files it reads.
  • Capability inventory: The skill executes read-only shell commands and suggests code modifications or the use of the sentry-wizard tool.
  • Sanitization: No explicit sanitization or filtering is performed on the data retrieved from local files during the discovery phase.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 11:45 AM