qa-engineer-agent
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: Detailed analysis of the skill content reveals no malicious behavior, hardcoded credentials, or unauthorized network operations. The instructions align with the stated purpose of assisting in quality assurance and software testing.
- [NO_CODE]: The skill does not provide any executable scripts (e.g., .sh, .py, .js) or compiled binaries. It relies entirely on the host agent's existing capabilities to interpret the Markdown-based guidelines.
- [PROMPT_INJECTION]: The skill defines a surface for processing untrusted data, such as project requirements and source code, which represents an indirect prompt injection risk factor.
- Ingestion points: The workflow involves reading external requirement documents and source code to generate test cases (SKILL.md).
- Boundary markers: No specific delimiters or warnings against embedded instructions are provided for processed data.
- Capability inventory: The skill configuration for Claude Code requests tools for file system interaction (
read,write,edit) and shell command execution (bash). - Sanitization: No input validation or sanitization steps are defined for external data sources.
Audit Metadata