workflow-e2e-update-ui

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill instructs the agent to pass the user's prompt as context to the /workflow-start command, which constitutes an indirect prompt injection surface.
  • Ingestion points: User prompt is passed to the e2e-update-ui workflow via the /workflow-start command in SKILL.md.
  • Boundary markers: Absent; user input is used as context without delimiters or instructions to ignore embedded commands.
  • Capability inventory: The triggered workflow has the capability to execute a sequence of commands including /scout, /e2e-test, and /test.
  • Sanitization: No sanitization or validation of the user-provided content is performed before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 07:25 AM
Security Audit — agent-trust-hub — workflow-e2e-update-ui