tensorrt-llm
What this skill does
High-throughput LLM inference on NVIDIA GPUs using TensorRT-LLM
github/nousresearch - Insecure Default Configuration - 228.4k stars
Threat analysis
Skill info
pkg:github/NousResearch/hermes-agent@49c6323?skill=tensorrt-llmAssessments (2)
Insecure Default Configuration
Insecure Default Configuration via local-llm-review
references/serving.md
The API key is optional and not enforced by default in the example configuration. This could allow unauthorized access to the model if not properly secured in production.Information Disclosure
Information Disclosure via local-llm-review
references/serving.md
The example shows a basic usage without any authentication, which could expose the model to unauthorized requests if deployed without proper security measures.Badge
Add the Anomity scan badge for tensorrt-llm 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 tensorrt-llm? Report an issue or request a rescan.
