macos-test-triage
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted test logs and assertion messages, creating a surface for indirect prompt injection.
- Ingestion points: Data enters the context via xcodebuild and swift test outputs as described in SKILL.md.
- Boundary markers: No delimiters or instructions are provided to the agent to distinguish between tool output and potentially malicious instructions embedded in logs.
- Capability inventory: The skill uses subprocess calls to execute standard developer test harnesses.
- Sanitization: No validation or escaping is applied to the incoming test results prior to analysis.
Audit Metadata