nix

Warn

Audited by Snyk on May 10, 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). The SKILL.md includes explicit runtime commands that fetch and process arbitrary web content (e.g., "Prefetching Hashes" shows nix-prefetch-url --unpack https://example.com/source.tar.gz and "Shebang Scripts" shows curl -s https://example.com), so the agent could ingest untrusted third‑party data that might materially influence builds or subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 10, 2026, 01:17 PM
Issues
1