user-advocate
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFE
Full Analysis
- Instructional Focus: The skill consists entirely of behavioral and tonal instructions for the agent. It does not contain any executable scripts, binaries, or command-line operations that could interact with the host system.
- External Resource Assessment: No remote scripts, external downloads, or third-party packages (Python or Node.js) are referenced. The skill operates exclusively within the provided prompt context and standard agent capabilities.
- Data Security: There are no hardcoded credentials, sensitive file paths, or persistence mechanisms detected. The skill instructions focus on analyzing project documentation (such as briefs and feedback) to advocate for user needs.
- Interaction Surface: The skill is designed to process user-provided content like design plans or support threads. While this represents a standard data ingestion surface, the skill lacks the capabilities—such as network exfiltration or unauthorized file writing—that would be necessary to leverage an indirect prompt injection for malicious purposes.
Audit Metadata