investigate

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt requires appending "raw data verbatim" (log lines, command output, stack traces) into a logfile using heredocs, which forces the agent to reproduce any secrets present in inputs verbatim.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly solicits user-provided URLs and supporting materials in Step 1 and designates a "Researcher" sub-agent to perform information gathering (Roles / Workflow Step 4), so the agent is expected to ingest and act on arbitrary public third‑party content that could influence subsequent decisions.