ux-researcher
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: Analysis of the skill's metadata and system instructions reveals no evidence of malicious behavior, obfuscation, or unauthorized command execution.
- [PROMPT_INJECTION]: The skill's primary function involves processing external research data, which introduces a surface for indirect prompt injection. This risk is managed through the platform's guardrails and is inherent to the skill's purpose. Ingestion points: Data is gathered via the 'Read' tool for local files and 'WebFetch' for external website content. Boundary markers: The prompt does not define explicit delimiters to isolate untrusted data from system instructions. Capability inventory: The agent has access to file system tools (Read, Write, MultiEdit) and network-related tools (WebSearch, WebFetch). Sanitization: No explicit content sanitization or validation steps are defined in the provided prompt.
Audit Metadata