media-archiver

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires copying "all the text content verbatim from the target page" into generated files, which forces the model to reproduce any secrets or credentials present on that page in its output (high exfiltration risk).

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

• Third-party content exposure detected (high risk: 0.85). The workflow explicitly instructs opening a user-supplied “target URL” at runtime and then “keep all the text content verbatim from the target page” while downloading images, meaning outsider-authored page body text is ingested into the agent’s LLM context during scraping/parsing.