sentry-cocoa-sdk
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads project files (e.g., Package.swift, Podfile, AppDelegate.swift) to provide tailored integration advice. This represents a potential surface for indirect prompt injection where malicious content in those files could influence the agent's behavior. * Ingestion points: Phase 1 and Phase 4 use grep and ls commands to scan the local project structure. * Boundary markers: The skill does not use specific delimiters or warnings to ignore embedded instructions in the scanned files. * Capability inventory: The skill utilizes shell commands (bash) for detection and suggests code snippets for the user to implement. * Sanitization: No sanitization or validation is performed on the data read from the files.
- [COMMAND_EXECUTION]: The skill uses local shell commands to detect project frameworks, platforms, and existing dependencies.
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the sentry-wizard CLI tool and the sentry-cocoa SDK from official repositories. These resources are hosted on well-known platforms (Homebrew, GitHub) and align with the stated vendor identity.
Audit Metadata