SkillPedia Skills Encyclopedia
中文 EN

DeepSecUnclecheng-li/DeepSec

A composable security-testing skill pack that lets AI agents run penetration testing and vulnerability verification with…

No ratings yet Rate this skill
Stars475
Forks30
Watchers475
Open Issues7

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/Unclecheng-li/DeepSec.git

OverviewOverview

Key Features

A composable security-testing skill pack that lets AI agents run penetration testing and vulnerability verification within controlled boundaries. Key capabilities include: 1. Target allowlist control: the targets skill restricts which assets an agent may test (supports https://domain, bare domains, and *.domain wildcards), keeping probing confined to authorized scope; 2. Dangerous CIDR blocking: the prohibited_cidrs skill blocks private, loopback, and link-local addresses by default, preventing agents from hitting internal networks or local services; 3. Insecure code pattern detection: built-in checks for unsafe calls such as yaml.load() and innerHTML help locate deserialization and XSS-class vulnerabilities; 4. Feedback channels: the report-bug, feature-request, and submit-PR skills route findings and improvement suggestions back into the project.

Use Cases

Executing authorized penetration tests, constraining asset scope during red team assessments, reproducing and verifying vulnerabilities, and wiring security testing into automated AI agent orchestration.

Target Roles

Network & System Security Engineer, Test / QA Engineer, AI / Algorithm Engineer, Backend Developer.

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 ID1904
Data sourceGitHub
RepositoryUnclecheng-li/DeepSec
CategoryNetwork & System Security / Penetration Testing & Vulnerability Discovery
Primary languagePython
LicenseMIT License
Default branchmain
GitHub repository ID1295322882
Node IDR_kgDOTTUPAg
Rank#1318 (position within the source ranking)
Site-wide popularity rank#1507 (computed live from Stars, across all 5845 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

02004006002026-09-292026-10-112026-09-29 · 4512026-10-11 · 475
  • Now475
  • Previous point · 09-29 451
  • vs previous point +24
  • 2 data points 12 days
01020302026-09-292026-10-112026-09-29 · 302026-10-11 · 30
  • Now30
  • Previous point · 09-29 30
  • vs previous point ±0
  • 2 data points 12 days

TimelineTimeline

Repository created2026-07-09 13:53:544 months ago
Data last updated2026-10-26 12:12:2224 days ago
Last commit2026-08-24 15:04:512 months ago

CommitLatest commit

Version [v0.2.0] committed by Unclecheng-li. Update Category: Feature Addition & Enhancement. Commit details: Merge pull request #9 from Unclecheng-li/feat/dsh-plugins. This update introduces new capabilities and module extensions.

fff031f v0.2.0 Unclecheng-li 2026-08-24

Next stepsNext steps