e2e-flow-verifier

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data and variables to drive browser automation, which introduces a surface for indirect instructions.
  • Ingestion points: User-defined flow parameters (e.g., base_url, test_user, expected_text) are interpolated into JSON batch files and shell commands within SKILL.md.
  • Boundary markers: None are present in the provided templates to isolate user-supplied data from the command execution flow.
  • Capability inventory: The skill executes the vibium binary for browser interaction, runs local Node.js scripts (batch.js, assert.js), and performs file writes to /tmp and test-results/.
  • Sanitization: There is no evidence of sanitization or validation for the interpolated variables within the skill instructions.
  • [COMMAND_EXECUTION]: The skill provides instructions to execute local binaries and scripts to perform its primary function.
  • Execution details: It invokes the vibium CLI for recording browser sessions (vibium record) and restoring session state (vibium storage). It also utilizes node to execute scripts located in .claude/skills/qe-browser/ for batch processing and state assertions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 06:15 PM
Security Audit — agent-trust-hub — e2e-flow-verifier