# NVIDIA/SkillSpector

Source: [GitHub](https://github.com/NVIDIA/SkillSpector)  
Feed7 permalink: https://feed7.dev/p/skillspector-1o8ny3i  
Published: Unknown  
Trust: Needs Review (needs_review)

## Why Included

SkillSpector scans agent skills for security risks before installation, with static checks, optional LLM analysis, and reports that can feed CI. Its cited research subset found vulnerabilities in 26.1% of skills.

## Source Summary

SkillSpector checks skills from repositories, URLs, archives, directories, or files using **71 vulnerability patterns across 17 categories**. It combines static analysis with optional LLM review and can emit SARIF, JSON, Markdown, or terminal reports. The cited dataset subset contained 31,132 skills; **26.1% had vulnerabilities** and 5.2% showed likely malicious intent.
Add a scan before installing third-party skills, or use SARIF and `--fail-on-incomplete` to support CI gates. Baselines can suppress findings already reviewed so later scans surface new ones.
A scanner report is a review aid, not proof a skill is safe. Findings can be suppressed, and caller exclusions make coverage partial and prevent a SAFE recommendation. LLM analysis is optional and requires provider configuration.

## Practical Implication

No separate implication recorded.

## Agent-Ready Context

SkillSpector checks skills from repositories, URLs, archives, directories, or files using **71 vulnerability patterns across 17 categories**. It combines static analysis with optional LLM review and can emit SARIF, JSON, Markdown, or terminal reports. The cited dataset subset contained 31,132 skills; **26.1% had vulnerabilities** and 5.2% showed likely malicious intent.
Add a scan before installing third-party skills, or use SARIF and `--fail-on-incomplete` to support CI gates. Baselines can suppress findings already reviewed so later scans surface new ones.
A scanner report is a review aid, not proof a skill is safe. Findings can be suppressed, and caller exclusions make coverage partial and prevent a SAFE recommendation. LLM analysis is optional and requires provider configuration.

## Connected Context

Feed7 judgment across 910 accumulated Signals:

This makes third-party skill review a repeatable scanning step, with CI output and baselines to track newly surfaced findings. Its dataset figures give scale to the exposure concern, while the caveats matter operationally: a clean report is not a safety guarantee, and exclusions can leave coverage incomplete.

- [We Vetted 2000 AI Skills Before They Reached Developers — Lucas Palma, Nubank](https://feed7.dev/p/we-vetted-2000-ai-skills-before-they-reached-developers-lucas-palma-nuba-0k4ehkz) — Both treat skills as supply-chain dependencies and describe scanning in operational workflows; SkillSpector adds concrete scan inputs, report formats, baselines, and an explicit limit on what a clean result proves.
- [anthropics/claude-plugins-community](https://feed7.dev/p/claude-plugins-community-0vhi4d8) — The reviewed plugin mirror screens entries before distribution, while SkillSpector offers a scanner teams can use for their own review; scanning alone does not establish the mirror's unspecified review criteria or behavioral guarantees.
- [VoltAgent/awesome-agent-skills](https://feed7.dev/p/awesome-agent-skills-0vfknie) — The discovery index makes selective adoption important, and SkillSpector supplies a way to inspect candidate skills before installing them; neither catalog inclusion nor scan results replace broader evaluation.
- [zhaoxuya520/reverse-skill](https://feed7.dev/p/reverse-skill-1e4jlfw) — The security router's broad skill-pack concern is directly addressed by independent scanning, while its authorization and evidence workflow covers risks a static or optional LLM scan cannot resolve.

## Context Map

- Layer: tools
- Domains: coding, security
- Topics: skills, tool-use

## Uncertainty

- None recorded.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.