a2ui-test-quality-check
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external test files which represents an indirect prompt injection attack surface.\n- Ingestion points: Test directories and files (e.g., tests/, test/, *Tests.swift) as specified in SKILL.md.\n- Boundary markers: The instructions do not define specific markers or delimiters to separate the untrusted code content from the agent's internal instructions.\n- Capability inventory: The skill is limited to code analysis and reporting; no high-privilege tool execution or network capabilities are requested in the instructions.\n- Sanitization: No instructions are provided for sanitizing or filtering input from the audited code files.
Audit Metadata