axiom-debug-tests
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands such as
xcodebuild,xcrun, andxcsymto execute test suites, manage simulators, and analyze crash reports. - [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and processes external data from test logs and failure artifacts.
- Ingestion points: Failure logs (
/tmp/xcodebuild-debug.log), console output (console.log), and test results (test-results.txt) read during analysis phases. - Boundary markers: The instructions do not specify the use of delimiters or markers to isolate external log data from the agent's internal prompt context.
- Capability inventory: The agent is capable of executing shell commands and modifying project files using the Edit tool.
- Sanitization: There is no mention of sanitization or validation performed on the log content prior to its analysis by the agent.
Audit Metadata