hugging-face-model-trainer
What this skill does
Training and fine-tuning language models using Hugging Face infrastructure, with support for GGUF conversion for local deployment.
github/sickn33 - Obfuscation - 43.8k stars
Threat analysis
Skill info
pkg:github/sickn33/agentic-awesome-skills@11c9e67?skill=hugging-face-model-trainerAssessments (2)
Obfuscation
Obfuscation via local-llm-review
SKILL.md
Skill source points to a Hugging Face skill repository, which may be obfuscating the actual originPrivilege Escalation
Privilege Escalation via local-llm-review
scripts/convert_to_gguf.py
PREREQUISITES section recommends using 'sudo' to install system packagesBadge
Add the Anomity scan badge for hugging-face-model-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 hugging-face-model-trainer? Report an issue or request a rescan.
