test-triage
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses local shell commands such as xcodebuild test and swift test to perform test triage. This behavior is consistent with the primary purpose of the skill.
- [PROMPT_INJECTION]: The skill processes external, potentially untrusted test output which creates a surface for indirect prompt injection. 1. Ingestion points: Test logs, assertion messages, and crash signals (SKILL.md). 2. Boundary markers: No explicit delimiters are present to isolate test data from the agent's instruction context. 3. Capability inventory: Execution of developer tools and shell commands for rerunning tests. 4. Sanitization: There is no evidence of sanitization or escaping of the ingested test data before it is analyzed.
Audit Metadata