CF nemo-guardrails
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.
NVIDIA's runtime safety framework for LLM applications.
As a process F 33/100 · No process to follow — References files that are not bundled: references/colang-guide.md, references/integrations.md, references/performance.md
How to improve
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 4
✓ No critical or high findings
Medium and low: 4
-
low Instruction override
en-ignore-previousSKILL.md:65Instruction-override phrase ("ignore previous instructions") (negated — the text forbids it)"I cannot bypass my safety guidelines."
negated
A further 3 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/colang-guide.md - warning
missing-refreference to a missing file: references/integrations.md - warning
missing-refreference to a missing file: references/performance.md - note
frontmatter-keyunknown frontmatter key "dependencies"
Process rating: all ten parameters 33/100
- 0Tools and files. 3 referenced file(s) missing: references/colang-guide.md, references/integrations.md, references/performance.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 100Steps. 29 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1772 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 263: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (10 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.