pp-paul-graham

Warn

Audited by Snyk on Jul 20, 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). This skill’s required workflow can invoke paul-graham-pp-cli read/search/latest which fetches paulgraham.com essay pages / “full text” at runtime (public web content) and then returns extracted readable text via the CLI to the agent, which becomes LLM-visible context—an outsider-authored free-text source.

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

  • Potentially malicious external URL detected (high risk: 0.80). The skill requires installing and running remote packages at runtime—e.g., "npx -y @mvanhorn/printing-press-library install paul-graham --cli-only" and the go install commands "go install github.com/mvanhorn/printing-press-library/.../paul-graham-pp-cli@latest" and "go install github.com/mvanhorn/printing-press-library/.../paul-graham-pp-mcp@latest"—which fetch and execute remote code and are required for the skill to operate.

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
Jul 20, 2026, 10:59 PM
Issues
2
Security Audit — snyk — pp-paul-graham