playwright-trace-analyzer

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires extracting and reporting raw trace contents (e.g., "console / page errors captured verbatim" and network snapshots/requests), which forces the agent to read and potentially emit secrets (API keys, cookies, tokens) found in traces.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests third-party artifacts from GitHub Actions (see scripts/fetch-gh-run.mjs and the "Input is a GitHub Actions run URL" flow) and then parses untrusted, user-generated trace contents (trace.trace / trace.network, console/page errors) which the agent must read and use as evidence to drive root-cause analysis and fix recommendations, so those external files could carry crafted instructions that influence the agent's actions.