Independent publisher
Prismor
prismor
Prismor is an open-source, independent control plane for AI agents. It helps enterprises control agent identity, access, and runtime actions by intercepting every tool call before execution, enforcing policy, protecting secrets, and recording a full audit trail across coding agents, SDKs, and MCP workflows.
Models in Library1
Datasets in Library0
Models on Hugging Face1
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Text classification.
Reported licenses: apache-2.0. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.
Models
Model · Text classification
Prismor
A prompt injection detector fine-tuned from Qwen2.5-1.5B-Instruct using LoRA on ~10,000 labeled examples. Given an input prompt, the model outputs INJECTION or SAFE. This model is analyzed in the paper: When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift. The associated research repository can be found at github.com/maxf-zn/prompt-mining. Trained and evaluated by Prismor as part of a runtime security layer for LLM-powered applications. Evaluated on the fully independent rogue-security/prompt-injections-benchmark — 5,000 samples, no model was trained on this data. This is the most honest comparison available. - Our model leads on F1 (0.726) and AUC…
Open weights
apache-2.0
1.5B parameters
32,768 tokens
transformers