E2E Test Runner

Pass

Audited by Gen Agent Trust Hub on Jun 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local build processes via 'make e2e' and runs the resulting test binary './bin/test-e2e'. It also uses container tools ('podman' or 'docker') to build and push images as part of the iteration loop.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it instructs the agent to analyze untrusted data generated by the cluster during tests.
  • Ingestion points: The agent reads logs, events, and resource states from the '$E2E_ARTIFACT_DIR/' directory after test failures.
  • Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded in the logs.
  • Capability inventory: The skill allows for command execution, binary execution, and network operations (pushing images).
  • Sanitization: No validation or sanitization of the cluster output is performed before the agent processes it for debugging.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 6, 2026, 04:59 PM
Security Audit — agent-trust-hub — E2E Test Runner