nutrient-document-processing

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes explicit examples that pass secrets as literals (export NUTRIENT_API_KEY="nutr_sk_..." and CLI flags like --user-password upass / --owner-password opass), which would require the agent to handle or reproduce secret values verbatim in commands or code.

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

• Third-party content exposure detected (high risk: 0.90). The skill accepts arbitrary URLs as inputs in multiple required scripts (e.g., --input in scripts/convert.py, scripts/extract-text.py, scripts/merge.py and the template assets/templates/custom-workflow-template.py uses add_file_part(args.input)), so it fetches and ingests untrusted public third-party documents which the tool reads and returns/exposes parsed content that could be used to drive subsequent actions.