Skip to main content

add-llama-cpp

Installs and configures a local llama.cpp server for efficient text generation experiments, integrating with Deus for enhanced performance.

Install this skill

or
46/100

Security score

The add-llama-cpp skill was audited on Jun 1, 2026 and we found 26 security issues across 4 threat categories. Review the findings below before installing.

Categories Tested

Security Issues

medium line 78

Template literal with variable interpolation in command context

SourceSKILL.md
78```bash
medium line 26

Curl to non-GitHub URL

SourceSKILL.md
26curl -fsS http://127.0.0.1:8080/health 2>/dev/null || echo "llama-server not responding on 127.0.0.1:8080"
medium line 158

Curl to non-GitHub URL

SourceSKILL.md
158curl -fsS http://127.0.0.1:8080/health
medium line 159

Curl to non-GitHub URL

SourceSKILL.md
159curl -fsS http://127.0.0.1:8080/v1/models
medium line 165

Curl to non-GitHub URL

SourceSKILL.md
165curl -fsS http://127.0.0.1:8080/v1/chat/completions \
medium line 259

Access to hidden dotfiles in home directory

SourceSKILL.md
259If the chosen Hugging Face preset is invalid, switch `LLAMA_CPP_MODEL` in `~/.config/deus/llama-cpp.env` to a known-good preset and restart the service.
low line 67

Access to .env file

SourceSKILL.md
67cat > "$HOME/.config/deus/llama-cpp.env" <<'EOF'
low line 83

Access to .env file

SourceSKILL.md
83ENV_FILE="$HOME/.config/deus/llama-cpp.env"
low line 201

Access to .env file

SourceSKILL.md
201if grep -q '^LLAMA_CPP_BASE_URL=' .env 2>/dev/null; then
low line 202

Access to .env file

SourceSKILL.md
202tmpf=$(mktemp) && sed 's#^LLAMA_CPP_BASE_URL=.*#LLAMA_CPP_BASE_URL=http://127.0.0.1:8080#' .env > "$tmpf" && mv "$tmpf" .env
low line 204

Access to .env file

SourceSKILL.md
204echo 'LLAMA_CPP_BASE_URL=http://127.0.0.1:8080' >> .env
low line 207

Access to .env file

SourceSKILL.md
207if grep -q '^LLAMA_CPP_MODEL=' .env 2>/dev/null; then
low line 208

Access to .env file

SourceSKILL.md
208tmpf=$(mktemp) && sed 's#^LLAMA_CPP_MODEL=.*#LLAMA_CPP_MODEL=ggml-org/gemma-3-1b-it-GGUF:Q4_K_M#' .env > "$tmpf" && mv "$tmpf" .env
low line 210

Access to .env file

SourceSKILL.md
210echo 'LLAMA_CPP_MODEL=ggml-org/gemma-3-1b-it-GGUF:Q4_K_M' >> .env
low line 213

Access to .env file

SourceSKILL.md
213mkdir -p data/env && cp .env data/env/env
medium line 259

Access to .env file

SourceSKILL.md
259If the chosen Hugging Face preset is invalid, switch `LLAMA_CPP_MODEL` in `~/.config/deus/llama-cpp.env` to a known-good preset and restart the service.
low line 279

Access to .env file

SourceSKILL.md
279rm -f "$HOME/.config/deus/llama-cpp.env"
low line 26

External URL reference

SourceSKILL.md
26curl -fsS http://127.0.0.1:8080/health 2>/dev/null || echo "llama-server not responding on 127.0.0.1:8080"
low line 118

External URL reference

SourceSKILL.md
118<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
low line 158

External URL reference

SourceSKILL.md
158curl -fsS http://127.0.0.1:8080/health
low line 159

External URL reference

SourceSKILL.md
159curl -fsS http://127.0.0.1:8080/v1/models
low line 165

External URL reference

SourceSKILL.md
165curl -fsS http://127.0.0.1:8080/v1/chat/completions \
low line 202

External URL reference

SourceSKILL.md
202tmpf=$(mktemp) && sed 's#^LLAMA_CPP_BASE_URL=.*#LLAMA_CPP_BASE_URL=http://127.0.0.1:8080#' .env > "$tmpf" && mv "$tmpf" .env
low line 204

External URL reference

SourceSKILL.md
204echo 'LLAMA_CPP_BASE_URL=http://127.0.0.1:8080' >> .env
low line 225

External URL reference

SourceSKILL.md
225LLAMA_CPP_BASE_URL=http://127.0.0.1:8080 npx tsx setup/index.ts --step llama-cpp
low line 233

External URL reference

SourceSKILL.md
233LLAMA_CPP_BASE_URL=http://127.0.0.1:8080 python3 -m evolution.benchmark_generative \
Scanned on Jun 1, 2026
View Security Dashboard
Installation guide →
GitHub Stars 39
Rate this skill
Categorydevelopment
UpdatedJune 15, 2026
sliamh11/Deus