llmfit-hardware-model-matcher
Fail
Audited by Snyk on Mar 17, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E005: Suspicious download URL detected in skill instructions.
- Suspicious download URL detected (high risk: 0.80). Most URLs are local endpoints or common services (GitHub, a short domain, localhost/127.0.0.1), but the skill explicitly instructs running a remote install script (curl | sh) from https://llmfit.axjns.dev/install.sh and points to a GitHub repo/user that should be verified — direct shell downloads from an unvetted domain are a common malware vector, so treat this as suspicious until validated.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill documentation includes explicit steps that fetch and consume untrusted public content (e.g., "curl -fsSL https://llmfit.axjns.dev/install.sh | sh", git clone from GitHub, pulling images from ghcr.io, and model pulls via "ollama pull"), which the tool/agent is expected to run or use and therefore could materially influence actions or be a vector for indirect prompt injection.
Issues (2)
E005
CRITICALSuspicious download URL detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata