llama-cpp
llama.cpp local GGUF inference + HF Hub model discovery.
64
78%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./skills/mlops/inference/llama-cpp/SKILL.mdLow
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
This skill’s required runtime workflow explicitly instructs fetching Hugging Face “local-app” and page HTML/text (e.g., the `Hardware compatibility` section) from third-party repos, which is outsider-authored free-form text that would be placed into the agent/LLM context during extraction.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
I flagged these URLs because the skill explicitly instructs fetching and building remote code via git clone (https://github.com/ggml-org/llama.cpp and https://github.com/ggerganov/llama.cpp) and to fetch Hugging Face pages/API (https://huggingface.co/<repo>?local-app=llama.cpp and https://huggingface.co/api/models/<repo>/tree/main?recursive=true) at runtime to extract snippets/filenames that are then used to construct commands or run models, meaning external content is fetched during runtime and can directly control the agent's instructions or cause remote code to be executed.
- Repository
- NousResearch/hermes-agent
- Commit
b7a05b6
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.