pp-allrecipes

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

• Third-party content exposure detected (high risk: 0.90). The skill drives the allrecipes-pp-cli to fetch and parse public Allrecipes pages (e.g., "recipes get", "recipe ", "grocery-list <urls...>", "instructions ", "reviews " in the Command Reference) and consumes that JSON-LD/output in --agent mode to make selections, build grocery lists, and drive follow-up actions, so untrusted user-generated content from Allrecipes can directly influence agent behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires installing and executing a remote CLI fetched at runtime (e.g., via "go install github.com/mvanhorn/printing-press-library/library/food-and-dining/allrecipes/cmd/allrecipes-pp-cli@latest"), which downloads and runs external code that directly controls agent inputs/outputs.