Persona Walkthrough Specialist

Pass

Audited by Gen Agent Trust Hub on Oct 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The Persona Walkthrough Specialist skill consists entirely of markdown-based instructions for persona-driven UX analysis and audit reporting. No malicious patterns, command execution, or unauthorized network operations were detected in the skill content.
  • [INDIRECT_PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection due to its core function of processing untrusted web page content. Ingestion points: The skill is designed to analyze web page text and screenshots captured during audits (SKILL.md). Boundary markers: There are no explicit delimiters or safety instructions defined to isolate potentially malicious commands embedded within the analyzed web content. Capability inventory: The skill does not define or use high-risk tools such as subprocess execution, filesystem writes, or network requests. Sanitization: No sanitization or filtering of external data is specified. The risk is considered inherent to the skill's primary purpose and is not associated with dangerous capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 25, 2026, 03:57 AM