pp-lda-gov

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

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow is a CLI (lda-gov-pp-cli) that is triggered by free-form natural-language trigger phrases but it does not automatically ingest outsider-authored free text without the agent selecting a specific LDA.gov command/flags, since --agent is non-interactive and every input is a flag (the CLI then queries trusted LDA.gov data/API/local SQLite rather than consuming arbitrary external text from an inbox/feed).

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires installing remote binaries via Go module paths (github.com/mvanhorn/printing-press-library/.../cmd/lda-gov-pp-cli and .../cmd/lda-gov-pp-mcp), which cause fetching and executing remote code at setup/runtime and are required for the skill to operate.