ln-100-documents-pipeline

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt explicitly instructs extracting runbook "env_vars" and saving extracted facts (SOURCE_DOC_NOTES/.archive/extracted/) and merging them into coordinator input, which would cause any secret values present in those source docs to be ingested and could be emitted verbatim by the LLM.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly states that if the local shared/ directory is missing it will WebFetch required runtime-contract/reference files from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}, and those fetched "MANDATORY READ" documents are used at runtime to drive agent behavior (i.e., directly control prompts/instructions).