- Home
- Skills
- DevOps & Cloud
- Freebies — Basic Semgrep Linter
Works with the AI Agents you already use
Freebies — Basic Semgrep Linter
Run lightweight static analysis and OWASP security scans using sandboxed Semgrep runners.
Free
Freebies — Basic Semgrep Linter
Example session with this skill installed
Run a basic Semgrep scan on the current project to find any High or Critical security vulnerabilities in the source code.
- Read your context and instructions
- Compiled the freebies
I have inspected the workspace and generated a targeted Semgrep configuration to scan for high-risk patterns including hardcoded secrets, insecure TLS settings, and command injection vulnerabilities. The scan was executed via an ephemeral runner. ## Security Audit Findings | Severity | Vulnerability Type | File Path | Line | Description | | :--- | :--- | :--- | :--- | :--- | | **CRITICAL** | Hardcoded Secret | `src/config/db.js` | 12 | Potential plaintext password assigned to `DB_PASS`. | | **HIGH** | Insecure Command | `scripts/deploy.py` | 45 | Use of `os.system()` with unsanitized user input. | | **HIGH** | Weak Crypto | `src/auth.ts` | 89 | MD5 hash detected; use SHA-256 or higher for passwords. | | **MEDIUM** | Debug Mode | `app.py` | 5 | Flask `debug=True` found in production-ready file. | **Summary**: The scan identified 1 critical and 2 high-severity issues that require immediate attention. **Next steps** 1. Move the hardcoded password in `src/config/db.js` to a `.env` file. 2. Replace `os.system()` in `scripts/deploy.py` with the `subprocess` module using argument arrays. 3. Update `src/auth.ts` to use a secure hashing algorithm like Argon2 or bcrypt.
Connects securely to your tools. The creator never sees your data.
About this skill
Code audits often stall because setting up local security environments is a friction-heavy process. This skill eliminates that overhead by executing lightweight static analysis within your agent's sandbox using ephemeral runners. It identifies security antipatterns and OWASP vulnerabilities without requiring global package installations or elevated system privileges. ## What it does - **Automated Source Inspection** scans your repository workspace to identify target files for analysis. - **YAML Pattern Generation** creates standard Semgrep configuration files focused on common security flaws. - **Sandboxed Execution** runs scans through `npx`, `pipx`, or `uvx` to maintain environment isolation. - **Severity Mapping** categorizes findings into a Critical, High, Medium, and Low matrix. - **Precise Location Reporting** provides exact file paths and line numbers for every detected issue. ## How it works 1. **Analyze Workspace**: The skill inspects the local directory to determine the language and project structure. 2. **Define Rules**: It generates a `.semgrep.yaml` file containing patterns for common vulnerabilities like SQL injection or hardcoded secrets. 3. **Run Scan**: It executes the linter using a project-scoped runner like `npx semgrep`. 4. **Report Findings**: It parses the output into a structured severity matrix for immediate remediation. ## Frameworks & tools This tool uses Semgrep for static analysis and relies on project-scoped runners including `npx`, `pipx`, `uvx`, or `venv`. It is designed for DevSecOps workflows within sandboxed AI environments. ## Why this beats prompting it yourself Writing reliable Semgrep patterns manually is error-prone and time-consuming. This skill automates the configuration generation and ensures execution follows strict security guardrails, preventing the agent from attempting unauthorized global installs or privilege escalation. ## Use cases - Auditing pull requests for common OWASP Top 10 vulnerabilities. - Scanning for hardcoded credentials or API keys before a commit. - Running quick security checks in environments where you cannot install global tools. - Identifying deprecated or insecure function calls in legacy codebases. ## Known limitations Does not support cross-boundary taint analysis or deep data flow tracking. Analysis is strictly confined to the active project workspace and cannot access parent directories.
No cross-boundary taint analysis. No global package installs or root access. Workspace restricted to current directory.
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 any payment.
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
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 4 days ago
- Free with an Agensi account
Requires