axiom-run-tests
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for executing standard macOS/iOS development commands including
xcodebuild,xcrun simctl, andxcrun xcresulttool. These are necessary for the skill's primary purpose of running and analyzing mobile tests. - [INDIRECT_PROMPT_INJECTION]: The skill analyzes external data including test failure messages, console logs, and manifest files generated during the test run. While this data could theoretically contain instructions designed to influence the agent, the risk is inherent to any tool performing analysis. No unsafe interpolation into higher-privilege commands was observed.
- Ingestion points: Test logs (
xcresulttool get log), failure details (xcresulttool get test-details), and attachment manifests (manifest.json) are read into the agent context. - Boundary markers: The instructions use structured markdown sections to organize output but do not explicitly wrap external data in security-specific delimiters.
- Capability inventory: The agent utilizes shell command execution to perform its tasks.
- Sanitization: The skill does not explicitly sanitize the text content of logs or failure messages before analysis.
Audit Metadata