SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-17 UTC

No new commits yet today

Open the update feed

skill-scannercisco-ai-defense/skill-scanner

Performs multi-engine security scanning of agent skill packages to identify malicious behavior and risks before skills a…

No ratings yet Rate this skill
Stars2.6k
Forks331
Watchers2.6k
Open Issues2

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/cisco-ai-defense/skill-scanner.git

OverviewOverview

Key Features

Performs multi-engine security scanning of agent skill packages to identify malicious behavior and risks before skills are loaded and executed, preventing poisoned skills from reaching production. Key capabilities include: 1. Multi-Engine Detection: runs static analysis, behavioral dataflow tracing, and LLM semantic judgment engines together to cross-cover hidden risks that rules alone cannot describe; 2. Typed CEL Decisions: writes decision policies as typed CEL expressions that map scan results into explainable pass/block verdicts for audit traceability; 3. Measured Presets: ships tiered preset configurations by strictness so teams trade off false positives versus false negatives per scenario without tuning from scratch; 4. CI/CD and Pre-commit Integration: runs as a pipeline gate or local commit hook to block high-risk skills at merge or commit time; 5. Extensible Rules: supports custom detection rules and engine plug-ins to fit team-specific skill policies.

Use Cases

Pre-release security audit of agent skill packages, CI/CD pipeline security gates, local pre-commit risk interception, third-party skill marketplace admission review, LLM application supply chain risk assessment.

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 ID375
Data sourceGitHub
Repositorycisco-ai-defense/skill-scanner
CategoryNetwork & System Security / AI Supply Chain & Agent Security
Primary languagePython
LicenseOther
Default branchmain
GitHub repository ID1144727401
Node IDR_kgDORDsnaQ
Rank#374 (position within the source ranking)
Site-wide popularity rank#441 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

01k2k3k2026-09-302026-10-112026-09-30 · 2,5682026-10-11 · 2,589
  • Now2,589
  • Previous point · 09-30 2,568
  • vs previous point +21
  • 2 data points 11 days
01002003004002026-09-302026-10-112026-09-30 · 3242026-10-11 · 331
  • Now331
  • Previous point · 09-30 324
  • vs previous point +7
  • 2 data points 11 days

TimelineTimeline

Repository created2026-01-29 01:31:329 months ago
Data last updated2026-10-26 11:57:0621 days ago
Last commit2026-10-09 03:38:001 months ago

CommitLatest commit

Version [2.2.2] committed by vineethsai7. Update Category: Documentation Updates. Commit details: docs: pin site examples to skill-scanner 2.2.2 (#262). This update refines the documentation for easier onboarding.

f18074a v2.2.2 vineethsai7 2026-10-09

Next stepsNext steps