pp-openfda

Warn

Audited by Snyk on Jun 26, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.75). The required runtime workflow is to execute openfda-pp-cli ... --agent, which fetches FDA/OpenFDA data from the upstream API and returns it as JSON in stdout; that API-provided free-text fields (e.g., report narratives/labels) are outsider-authored content that the agent ingests into LLM context.

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill's prerequisite install commands fetch and execute remote code as required dependencies — specifically the npm package fetch via "npx -y @mvanhorn/printing-press-library install openfda --cli-only" and the Go module fetch "go install github.com/mvanhorn/printing-press-library/library/developer-tools/openfda/cmd/openfda-pp-cli@latest", so remote content would run during setup.

Issues (2)

W011
MEDIUM

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

W012
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 26, 2026, 03:57 PM
Issues
2
Security Audit — snyk — pp-openfda