SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-18 UTC

No new commits yet today

Open the update feed

SkillSpectorNVIDIA/SkillSpector

Performs static security auditing of AI agent skill packages (Skills / MCP plugins) to find prompt injection,…

No ratings yet Rate this skill
Stars20.9k
Forks1.8k
Watchers20.9k
Open Issues169

InstallOne-line install

Unconfirmed

Whether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:

git clone https://github.com/NVIDIA/SkillSpector.git

OverviewOverview

Key Features

Performs static security auditing of AI agent skill packages (Skills / MCP plugins) to find prompt injection, privilege escalation and data leakage risks before installation or release. Key capabilities include: 1. 71 vulnerability pattern matching: ships 71 vulnerability patterns targeting agent skills, compares them against skill files and pinpoints suspicious code and instructions with exact hit locations instead of vague alerts; 2. Two-stage analysis: runs a fast rule-based screening first, then a deeper semantic review of suspicious fragments to cut false positives and manual re-checks; 3. Live vulnerability lookups: queries up-to-date vulnerability intelligence during scanning so newly disclosed injection techniques and supply-chain risks are also caught; 4. Multi-format input and multiple output formats: accepts skill packages in multiple formats and exports results in several report formats for archiving or ticketing integration; 5. Risk scoring and quota control: assigns a risk score per skill and supports caps on per-ingest volume and zip member count so scanning huge repositories does not stall the pipeline.

Use Cases

Pre-release security audit of AI agent skill packages, risk screening before adopting third-party skills or MCP plugins, prompt-injection and privilege-escalation detection, batch scanning of skill repositories, automated security gates in CI.

Target Roles

Network & System Security Engineer, AI / Algorithm Engineer, DevOps / Operations Engineer, Test / QA Engineer.

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID85
Data sourceGitHub
RepositoryNVIDIA/SkillSpector
CategorySecurity & Compliance / AI Supply Chain Security
Primary languagePython
LicenseApache License 2.0
Default branchmain
GitHub repository ID1187630119
Node IDR_kgDORsnMJw
Rank#69 (position within the source ranking)
Site-wide popularity rank#85 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

010k20k30k2026-10-102026-10-222026-10-10 · 19,8192026-10-14 · 19,8192026-10-16 · 19,8192026-10-22 · 20,884
  • Now20,884
  • Previous point · 10-16 19,819
  • vs previous point +1,065
  • 4 data points 12 days
05001k1.5k2k2026-10-102026-10-222026-10-10 · 1,7352026-10-14 · 1,7352026-10-16 · 1,7352026-10-22 · 1,833
  • Now1,833
  • Previous point · 10-16 1,735
  • vs previous point +98
  • 4 data points 12 days

TimelineTimeline

Repository created2026-03-21 00:28:438 months ago
Data last updated2026-10-26 11:48:4923 days ago
Last commit2026-10-22 07:34:4127 days ago

CommitLatest commit

committed by mohgupta-ship-it. Category: Bug Fixes & Stability Improvements. Commit message: Merge pull request #844 from NVIDIA/yashraj/fix-release-scan-regressi….

e8850a8 mohgupta-ship-it 2026-10-16

Next stepsNext steps