pp-drug-enforcement

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

• Third-party content exposure detected (medium risk: 0.65). This skill runs a read-only “keyless” CLI that queries openFDA drug enforcement data at runtime, so any free-text fields returned by the outsider-authored public API (and/or echoed in agent-readable JSON/text) can enter the agent/LLM context via the CLI’s stdout/provenance output.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill's prerequisite/install steps invoke go install on remote modules which fetch and build/execute remote code (github.com/mvanhorn/printing-press-library/library/health/drug-enforcement/cmd/drug-enforcement-pp-cli@latest and github.com/mvanhorn/printing-press-library/library/health/drug-enforcement/cmd/drug-enforcement-pp-mcp@latest), meaning the skill can cause execution of externally fetched code required for operation.