Prompt Injection Scanner
- 245 installs
- 2 repo stars
- Updated January 25, 2026
- jorgealves/agent_skills
Scan user inputs, tool outputs, and RAG chunks for jailbreak and instruction-override patterns before they reach privileged agent tools or downstream models.
About
prompt-injection-scanner analyzes untrusted text bound for LLM agents and RAG pipelines to surface jailbreaks, hidden instructions, and tool-abuse attempts. It supports pre-release hardening of chat, email, and document ingestion paths where a single malicious payload could override system policies or leak secrets.
- Detects delimiter and role-manipulation payloads
- Flags indirect injection via retrieved documents
- Scores severity for blocking versus monitoring
- Suggests guardrail and sandbox mitigations
- Supports CI gates on representative attack sets
Prompt Injection Scanner by the numbers
- 245 all-time installs (skills.sh)
- +9 installs in the week ending Aug 2, 2026 (Skillselion tracking)
- Ranked #696 of 2,203 Security skills by installs in the Skillselion catalog
- Data as of Aug 2, 2026 (Skillselion catalog sync)
npx skills add https://github.com/jorgealves/agent_skills --skill prompt-injection-scannerAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 245 |
|---|---|
| repo stars | ★ 2 |
| Last updated | January 25, 2026 |
| Repository | jorgealves/agent_skills ↗ |
What it does
Scan user inputs, tool outputs, and RAG chunks for jailbreak and instruction-override patterns before they reach privileged agent tools or downstream models.
Files
Prompt Injection Scanner
Purpose and Intent
The prompt-injection-scanner is a security tool specifically for the AI agent era. It identifies weak points in agent instructions where a malicious user could potentially "hijack" the agent's behavior by inserting conflicting instructions into input fields.
When to Use
- Skill Development: Run this every time you update the
capabilitiesor instructions for an agent skill. - Pre-deployment Security Review: Essential before making an agent accessible to untrusted users.
- Continuous Security Auditing: Periodically scan all skills as new injection patterns are discovered.
When NOT to Use
- Standard Code Auditing: Use the
secret-leak-detectorfor credentials; this is specifically for "instruction-level" security.
Input and Output Examples
Input
skill_path: "./agent-skills/data-processor/SKILL.md"Output
A structured report highlighting parts of the instructions that are susceptible to prompt hijacking, along with concrete mitigation strategies.
Error Conditions and Edge Cases
- Missing Instructions: If a skill defines tools but provides no behavioral instructions, the scanner will flag this as a risk.
- Complex Logic: Highly conditional instructions can be difficult to model and may result in false positives or negatives.
Security and Data-Handling Considerations
- Metadata Focus: Only scans instructions; does not touch private user data.
- Local Analysis: Recommended to run locally within the development environment.
name: prompt-injection-scanner
version: 1.0.0
description: Audits agent skill instructions and system prompts for vulnerabilities to prompt hijacking and indirect injection. Use when designing new agent skills or before deploying agents to public environments where users provide untrusted input.
inputs:
skill_path:
type: string
description: Path to the SKILL.md or skill.yaml to analyze.
required: true
severity_threshold:
type: string
enum: [low, medium, high]
default: medium
outputs:
security_report:
type: object
properties:
vulnerabilities:
type: array
items:
type: object
properties:
type:
type: string
description:
type: string
mitigation:
type: string
capabilities:
- Pattern matching for common injection vectors (e.g., "Ignore previous instructions").
- Semantic analysis of instruction boundaries and variable usage.
- Verification of clear separation between instructions and user-provided data.
constraints:
- Heuristic analysis based on known injection patterns.
- Cannot guarantee 100% protection against novel or creative injection techniques.
security:
- Analyzes instruction text only; does not require access to live agent keys.
- Safe for local use during the development lifecycle.
examples:
- input:
skill_path: "./agent-skills/my-skill/SKILL.md"
output:
security_report:
vulnerabilities:
- type: "Instruction Overlap"
description: "Instruction block ends directly before a user variable without a delimiter."
mitigation: "Use clear delimiters like <input> tags."
Related skills
Entra App RegistrationCorrectly register an application in Microsoft Entra ID, configure OAuth 2.0 flows, request the right API permissions, and generate working MSAL authentication snippets484k1.3kAzure ComplianceRun automated Azure compliance scans, security posture checks, and Key Vault expiration audits before deploying.484k1.3k
Openclaw Secure Linux CloudDeploy and harden an OpenClaw agent instance on a Linux cloud server following battle-tested security defaults.270k72
Better Auth Best PracticesCorrectly configure Better Auth for secure authentication with database adapters, sessions, OAuth, email/password, and plugins in TypeScript projects.80.9k206
Firebase Security Rules AuditorAutomatically audit Firebase Firestore security rules for bypass vulnerabilities and logic gaps before deploying.80.4k397
Audit WebsiteRun comprehensive audits that surface SEO, performance, security, technical, and content issues with LLM-optimized reports and health scores.65.6k85