huggingface-local-models

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow fetches Hugging Face model pages and the ?local-app=llama.cpp page (public web content) and reads their text/HTML to extract quant recommendations, which can include outsider-authored free text from the model repo owners into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's Quick Start explicitly runs "git clone https://github.com/ggml-org/llama.cpp" followed by "make", which fetches and then executes remote code from https://github.com/ggml-org/llama.cpp during setup, meeting the criteria for a runtime external dependency that executes remote code.