audit-ux-journeys

Pass

Audited by Gen Agent Trust Hub on Oct 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from external websites via browser walkthroughs and from local source code files via search utilities. This creates an attack surface for indirect prompt injection where malicious instructions embedded in the audited content could attempt to influence the agent's behavior during the analysis phase.
  • Ingestion points: Phase 2 (headed browser walkthroughs of user stories) and Phases 0, 1, and 3 (source code scanning using fd and rg utilities) in SKILL.md and references/checklist.md.
  • Boundary markers: While the skill instructions provide structured reporting templates and reference a browser protocol, there are no explicit instructions for the agent to sanitize or treat extracted content as untrusted to prevent instruction override.
  • Capability inventory: The skill utilizes browser navigation, screenshot capture to the .playwright-mcp/ directory, and local file reading across the project structure.
  • Sanitization: The instructions do not specify any validation, filtering, or escaping techniques for the external data being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 19, 2026, 06:51 PM