ux-flow-auditor

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined task flows from JSON files to drive browser interactions and generate audit reports.
  • Ingestion points: scripts/trace_flow.py reads selector, value, and label fields from .heyeddi/docs/ux-flows/*.flow.json files, which are considered untrusted inputs from the repository.
  • Boundary markers: The resulting markdown report (.heyeddi/docs/ux-flows/<task>.md) lacks explicit boundary markers or warnings to distinguish between potentially untrusted content (like error messages or step labels) and the agent's instructions.
  • Capability inventory: The skill is capable of navigating web pages, performing UI actions via Playwright, capturing screenshots, and writing files to the local .heyeddi directory.
  • Sanitization: Data from the flow definitions and runtime error messages are interpolated directly into the markdown report without sanitization or escaping, creating a surface for indirect prompt injection when the agent processes the report to add 'friction notes'.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 03:38 AM
Security Audit — agent-trust-hub — ux-flow-auditor