software-ios-runtime-debugging
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard command-line tools for iOS development and troubleshooting.
- Suggests clearing project build caches by deleting the local DerivedData directory via
rm -rf ~/Library/Developer/Xcode/DerivedData/<ProjectName>-*(found inreferences/stale-build-triage.md). - Recommends using the
dangerouslyDisableSandbox: trueflag forxcodebuildto bypass build sandbox restrictions when necessary (found inSKILL.md). - Employs
security,codesign, andplutilto inspect application entitlements and provisioning profiles. - [EXTERNAL_DOWNLOADS]: The skill references documentation and configuration files from well-known and trusted sources.
- Fetches tool configurations and documentation from Sentry's official GitHub repository (
getsentry/XcodeBuildMCP). - References official Apple documentation and release notes for Xcode and iOS platform features.
- Points to established community forums and technical blogs for concurrency debugging research.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface by ingesting runtime data from a running application.
- Ingestion points: Ingests simulator logs through
simctl log streamand captures UI hierarchy and screenshots usingXcodeBuildMCP(described inSKILL.md). - Boundary markers: Absent; the instructions do not specify delimiters for separating log content from agent instructions.
- Capability inventory: Includes file system modification (deleting cache directories), compilation (
xcodebuild), and binary execution (simctl). - Sanitization: Absent; the skill does not include specific guidance for sanitizing or escaping runtime log data before interpretation.
Audit Metadata