Prompt Injection Scanner
This scans your agent instructions and system prompts for vulnerabilities where a user could slip in conflicting commands and hijack the agent's behavior. You'd run it when building new skills or before deploying agents that take untrusted input. It focuses specifically on instruction-level attacks, not code vulnerabilities or credential leaks. The output is a report pointing to risky sections with suggested fixes. One honest take: this addresses a real problem that's easy to overlook when you're heads-down building agents, especially since prompt injection patterns keep evolving. Worth running periodically on production skills, not just once at launch.
- skills.sh installs
- 270
- GitHub stars
- 2
- last updated
- Aug 21, 2026
Install
$ npx -y skills add jorgealves/agent_skills --skill prompt-injection-scanner --agent claude-codeInstalls into .claude/skills of the current project.
Files
This scans your agent instructions and system prompts for vulnerabilities where a user could slip in conflicting commands and hijack the agent's behavior. You'd run it when building new skills or before deploying agents that take untrusted input. It focuses specifically on instruction-level attacks, not code vulnerabilities or credential leaks. The output is a report pointing to risky sections with suggested fixes. One honest take: this addresses a real problem that's easy to overlook when you're heads-down building agents, especially since prompt injection patterns keep evolving. Worth running periodically on production skills, not just once at launch.
Browse the repository on GitHubSponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/jorgealves/agent_skills
- Category
- AI & Agent Building
- First seen
- Jun 3, 2026
More from jorgealves/agent_skills
All 19- Pii Sanitizer258
- Python Data Pipeline Designer258
- Documentation Generator255
- License Compliance Auditor243
- Hipaa Compliance Guard238
- Secret Leak Detector230
- Agent Capability Discovery226
- Module Learning Path Generator222
- Code Review Assistant221
- Python Performance Profiler220
- Skill Validator216
- Python Venv Manager215
- K8s Resource Optimizer213
- Python Async Advisor208
- Industry Standard Reviewer202
- Clinical Trial Schema Designer186
- Gdpr Ccpa Privacy Auditor408
- Python Security Scanner315
Recommended
More AI & Agent Building
cursor-subagent-creatortech-leads-club/agent-skillsCreates Cursor-specific AI subagents with isolated context for complex multi-step workflows. Use when creating subagents for Cursor editor specifically, followi259skills.sh installs
mcp-builderunclecatvn/agent-skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when b226skills.sh installs
subagent-task-executiondavidkiss/smart-ai-skillsUse when executing tasks from a task breakdown document in the current session.172skills.sh installs
copilot-docshoodini/ai-agents-skillsConfigure GitHub Copilot with custom instructions. Use when setting up .github/copilot-instructions.md, customizing Copilot behavior, or creating repository-spe147skills.sh installs