profiler-load-data

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). This skill reads an arbitrary file and "returns the file body unchanged" (raw text) as its output, so any secrets present in the file would be included verbatim in the LLM's output, creating an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). SKILL profiler-load-data reads filePath from caller input and uses System.IO.File.ReadAllText to ingest the local snapshot file’s raw contents (outsider-controlled only to the extent the caller supplies an arbitrary path), with no intermediary selection or filtering of file text.