pp-openfda
Warn
Audited by Snyk on Aug 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The source “SKILL.md” describes invoking
openfda-pp-cliread-only FDA/OpenFDA datasets via CLI commands (e.g.,animal-events,drug-events,device-recalls), but the workflow does not ingest outsider-authored free text except for user-selected query flags supplied at execution time and then used as parameters rather than as externally authored content read by the agent.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). This skill includes runtime installation commands that fetch and execute remote code — "npx -y @mvanhorn/printing-press-library install openfda --cli-only" and "go install github.com/mvanhorn/printing-press-library/library/developer-tools/openfda/cmd/openfda-pp-cli@latest" — which are required to provide the CLI the skill relies on.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata