axiom-xcode-mcp-tools
Warn
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defines workflows utilizing high-privilege tools such as
ExecuteSnippetfor running Swift code andXcodeRM/XcodeMVfor destructive file operations like deletion and moving within the project directory. - [EXTERNAL_DOWNLOADS]: The documentation references an untrusted third-party repository (
github.com/SoundBlaster/XcodeMCPWrapper) as a recommended solution for addressing MCP specification violations in some clients. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its pattern of processing external, potentially attacker-controlled data to drive automated tool loops.
- Ingestion points: Processes external data from build logs (
GetBuildLog), IDE diagnostics (XcodeListNavigatorIssues), and test execution results (RunSomeTests). - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the workflows when interpolating ingested data into subsequent logic.
- Capability inventory: Includes capabilities for file modification (
XcodeUpdate), file deletion (XcodeRM), and code execution (ExecuteSnippet). - Sanitization: No evidence of sanitization or validation of diagnostic/test output before it is used to determine 'fixes' or next steps in the BuildFix/TestFix loops.
Audit Metadata