test
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown documentation. It contains no executable code, script files, or requests for system permissions.\n- [PROMPT_INJECTION]: The skill includes 'Tell AI' blocks designed to guide agent behavior during testing tasks. These are legitimate instructional components that define how the agent should handle specific QA scenarios and bug-fixing tasks.\n- [DATA_EXFILTRATION]: Documentation within the skill references sensitive strings such as SQL injection payloads, XSS scripts, and local file paths (e.g., 'file:///etc/passwd') as examples of data the user should use to test their own applications. The skill itself does not attempt to access or exfiltrate any information from the environment.
Audit Metadata