qa-testing-ios
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The script
scripts/xcresult_to_junit.pyexecutes thexcresulttoolsystem utility usingsubprocess.runto extract test data. This is a standard and necessary operation for the skill's primary purpose of parsing Xcode test results. - [EXTERNAL_DOWNLOADS]: The skill documentation and
data/sources.jsonfile reference various external resources, including official Apple developer documentation, GitHub runner image specifications, and the well-knownswift-snapshot-testinglibrary from PointFree. These resources originate from trusted organizations and well-known services. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it processes external test result artifacts (
.xcresultbundles and converted JUnit XML) that could contain untrusted data. - Ingestion points: The conversion script
scripts/xcresult_to_junit.pyparses JSON output fromxcresulttool. The agent is subsequently instructed to triage failures based on the resulting artifacts. - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are present in the prompts that instruct the agent how to interpret the converted test results.
- Capability inventory: The agent has access to powerful command-line tools such as
xcodebuild,simctl, and the ability to execute Python scripts, which could be abused if the agent follows malicious instructions hidden in test failures. - Sanitization: The conversion utility extracts string values (test names and error messages) directly from the tool output without sanitization or filtering for potential prompt injection patterns.
Audit Metadata