pp-allrecipes

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly fetches and parses public Allrecipes pages (e.g., "allrecipes-pp-cli recipes get", "allrecipes-pp-cli recipe ", and the grocery-list <urls...> examples in SKILL.md) — user-generated/untrusted recipe pages and reviews are read and used by the agent to build grocery lists, cookbooks, rankings, and other decision-making outputs, so third-party content can materially 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 instructs runtime installation of and reliance on remote executables (via "npx -y @mvanhorn/printing-press" and "go install github.com/mvanhorn/printing-press-library/library/food-and-dining/allrecipes/cmd/allrecipes-pp-cli@latest" and "go install github.com/mvanhorn/printing-press-library/library/food-and-dining/allrecipes/cmd/allrecipes-pp-mcp@latest"), which fetch and execute remote code and are required for the skill to run.