gitnexus-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill documents a --api-key flag and shows the CLI can accept an API key on the command line (and thus encourages embedding secrets verbatim in generated commands), which is an insecure pattern that could force the LLM to output secret values directly.

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

• Third-party content exposure detected (high risk: 0.70). The runtime workflow for analyze parses “all source files” in the project and generates context files, so it can ingest outsider-authored free text (e.g., code/doc/comments from repos pulled from elsewhere) into LLM-readable context; this is not limited to user-authored content.