tutorial-harvesting-engine

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill explicitly extracts and outputs code blocks and tutorial content verbatim into a knowledge base, so any embedded API keys, tokens, or passwords in source materials could be captured and reproduced by the LLM.

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

• Third-party content exposure detected (high risk: 0.90). The skill’s required workflow ingests “sources” provided at runtime (URLs/files/directories) and then extracts/parses their tutorial content (public web pages or downloaded documents) into LLM-readable text for knowledge structuring, which is outsider-authored free text.