huggingface-llm-trainer
What this skill does
Training and fine-tuning language models using TRL (Transformer Reinforcement Learning) on Hugging Face infrastructure, with support for GGUF conversion for local deployment.
github/huggingface - Data Exfiltration - 10.9k stars
Threat analysis
Skill info
pkg:github/huggingface/skills@ec01082?skill=huggingface-llm-trainerAssessments (3)
Data Exfiltration
Data Exfiltration via local-llm-review
references/gguf_conversion.md
The skill's documentation includes code that runs `subprocess.run` with `apt-get` commands, which could be used to install malicious packages if the source is not trusted.MCP Least Privilege
MCP Least Privilege via local-llm-review
SKILL.md
The skill's documentation includes guidance on using `hf_jobs` with `secrets` and `HF_TOKEN`, which implies the use of privileged credentials. This could be a risk if not properly managed.MCP Rug Pull
MCP Rug Pull via local-llm-review
SKILL.md
The skill's documentation includes guidance on using `hf_jobs` with `secrets` and `HF_TOKEN`, which could be a rug pull if the token is mishandled or exposed.Badge
Add the Anomity scan badge for huggingface-llm-trainer to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of huggingface-llm-trainer? Report an issue or request a rescan.
