leanspec-publishing

Warn

Audited by Snyk on Mar 4, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). This skill's required publishing and verification workflow instructs the agent/operator to query and act on public third‑party sources (e.g., npm registry via commands like npm view ... and GitHub Releases pages/gh release operations such as https://github.com/codervisor/lean-spec/releases), and those external responses are explicitly used to decide publish/skip actions and next steps, exposing it to untrusted user-generated content that could carry indirect prompt-injection instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 06:06 AM