Book a 30-minute demo →
Skill scan report

nemo-retriever

View on GitHub
14 Low Automated analysis flagged 2 potential risk patterns.

What this skill does

Document retrieval and search across various file formats (PDFs, images, Office files, audio, video) using the NeMo Retriever Library.

github/nvidia - Security Misconfiguration - 2.8k stars

ThreatsSecurity Misconfiguration Information Disclosure

Threat analysis

Security Misconfiguration1 finding
Information Disclosure1 finding

Skill info

Namenvidia/nemo-retriever
Registrygithub
Versiona9ea6f9
PURLpkg:github/NVIDIA/skills@a9ea6f9?skill=nemo-retriever
Stars2.8k

Assessments (2)

Security Misconfiguration1 finding MEDIUM
MEDIUM

Security Misconfiguration via local-llm-review

scripts/filename_fast_path.py

The script reads from `./pdfs/` in the current working directory, which could be a security risk if the working directory is not properly controlled or if sensitive documents are stored there.
Information Disclosure1 finding LOW
LOW

Information Disclosure via local-llm-review

scripts/grep_corpus.py

The script outputs snippets of text from the corpus, which could potentially expose sensitive information if the corpus contains confidential data.

Badge

Add the Anomity scan badge for nemo-retriever to your README.

Anomity Skill Check badge

Markdown
[![Anomity Skill Check](https://anomity.ai/skills/badge.svg)](https://anomity.ai/skills/github/nvidia/nemo-retriever/)
HTML
<a href="https://anomity.ai/skills/github/nvidia/nemo-retriever/"><img src="https://anomity.ai/skills/badge.svg" alt="Anomity Skill Check"></a>
Image URL
https://anomity.ai/skills/badge.svg

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 nemo-retriever? Report an issue or request a rescan.

Ask AI about Anomity
ChatGPT Claude Perplexity Google AI Grok