More screenshots
Works with the AI Agents you already use
SentryKit Core
Offline security auditor for finding secrets, risky code patterns, and dependency flaws within your coding agent.
$12
SentryKit Core
Example session with this skill installed
Run a full security scan on the current repository. Triage all findings and generate patches for anything High or Critical. Mask all secrets.
- Read your context and instructions
- Compiled the sentrykit core
I have completed a full security scan of the repository. I ran the secret, pattern, and dependency scanners, triaged the hits, and performed a manual logic review of the API handlers.
Security Audit Report: sentrykit-report
| Severity | Count | Key Risks Identified |
|---|---|---|
| Critical | 1 | Hardcoded AWS Production Secret in config/env.js |
| High | 1 | Potential SQL Injection in lib/db.py via unsanitized user input |
| Medium | 1 | Unpinned dependency version for express in package.json |
| Low | 2 | Missing security headers; Debug mode enabled in development |
Confirmed Findings
[SK-0001] Hardcoded AWS Secret Key
- Location:
config/env.js:14 - CWE: CWE-798 (Use of Hard-coded Credentials)
Exploit: An attacker who gains access to the source code can use the AKIA**** key to gain full access to the production S3 buckets.
- Fix: Move the secret to an environment variable.
// sentrykit-report/patches/SK-0001.patch
--- a/c
Connects securely to your tools. The creator never sees your data.
About this skill
Security vulnerabilities and hardcoded secrets often slip into codebases unnoticed, only to be caught after a breach or a failed compliance audit. SentryKit provides an offline, deterministic security review workflow that runs directly within your coding agent to identify, triage, and patch critical flaws before they reach production.
What it does
- Secrets scanning detects provider keys, JWTs, PEM files, and high-entropy strings with automatic masking for safe reporting.
- Pattern analysis identifies SQLi, XSS, unsafe deserialization, shell injection, and unauthenticated routes across multiple languages.
- Dependency auditing flags unpinned versions, suspicious package sources, and integrates with local audit tools for CVE detection.
- Manual logic hunting guides the agent to find complex flaws like IDOR, race conditions, and prompt injection that scripts miss.
- Automated patching generates unified-diff
.patchfiles for confirmed findings based on a remediation playbook.
How it
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Security.
Offline scanning only. No dynamic analysis (DAST) or runtime testing. Dependency CVE lookups require local npm/pip-audit tools and user opt-in for network access.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 days ago
- Accounts
GitHub
Yarnpkg
Crates
- Software
Git
Permissions
Allowed Hosts