k6-perf-test-website

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly requires eliciting and recording "credentials" into the runbook and instructs replacing session/session tokens in scripts, which forces the agent to handle secret values verbatim (high exfiltration risk).

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The runtime path includes user-authored workflow text stored in runbook.md (e.g., target URL/constraints and workflow descriptions from §1 elicitation), which the workflow then uses to parameterize Playwright/k6 scripts and decide what traffic to record/test.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The k6 test templates import and therefore fetch+execute remote JS modules at runtime from https://jslib.k6.io/k6-testing/0.5.0/index.js and https://jslib.k6.io/k6-utils/1.5.0/index.js, which the skill relies on for assertions and async checks, so these URLs are runtime external dependencies that execute remote code.