Pricing

from $0.50 / 1,000 scanned documents

Go to Apify Store

Prompt Injection Web Scanner

Try for free

Scan webpages or text for prompt injection, secret exfiltration, hidden instructions and Unicode control characters.

Pricing

from $0.50 / 1,000 scanned documents

Rating

0.0

(0)

Developer

Q Services

Actor stats

Bookmarked

Total users

Monthly active users

4 days ago

Last modified

Input

Provide startUrls, texts, or both. maxResults caps processing and billing.

Output

One result per document with riskLevel, riskScore, and an explainable findings array. Network failures remain visible as riskLevel: unknown.

Pricing

Pay per event: $0.005 per run plus $0.0005 per document.

Limitations

This is a deterministic screening layer, not a proof of safety. Obfuscated or novel attacks can evade static rules, and benign security documentation can trigger findings.

Prompt Injection Firewall MCP

reverberant_equality/mcp-prompt-injection-firewall

Heuristically scan untrusted text and public web pages for prompt-injection patterns, flag suspicious instructions, and separate them from retained content for safer AI-agent workflows.

Jordan C

Prompt Injection Dataset Scanner v2

zentrafoundry/prompt-injection-dataset-scanner-v2

Inspect prompt injection dataset scanner v2 workflows and return policy decisions, risk flags, cost notes, trace evidence, and recommended actions.

Zentra

Prompt Injection Dataset Scanner

zentrafoundry/zentra-prompt-injection-quarantine

Scan and sanitize dataset records before they enter LLM, RAG, or agent pipelines.

Zentra

Agent-Safe Webpage Extractor

q_services/agent-safe-webpage-extractor

Convert webpages to compact Markdown with provenance, token estimates and prompt-injection risk flags for AI agents.

Q Services

MCP Server Risk Auditor

trovevault/mcp-server-risk-auditor

Audits MCP server manifests for tool, permission, credential, prompt-injection, exfiltration, and execution risks. Export data, run via API, schedule and monitor runs, or integrate with other tools.

Trove Vault

Unicode Text Inspector

maximedupre/unicode-text-inspector

Inspect pasted text for hidden Unicode characters, zero-width spaces, bidi controls, control characters, and homoglyphs. Get risk levels, issue evidence, category counts, cleaned text, and batch summaries.

Maxime Dupré

Prompt Injection & Jailbreak Payload Corpus

jungle_synthesizer/prompt-injection-jailbreak-payload-corpus-scraper

Normalizes published prompt-injection and jailbreak datasets from HuggingFace and GitHub research repos into one labeled corpus: technique, target model, defense bypassed, license, cross-source dedup. Defensive only — aggregates public data for guardrail/eval testing, never targets a live LLM.

BowTiedRaccoon

Claude Prompt Library Scraper

bornoo/claude-prompt-library-scraper

Scrape prompts from the Claude Prompt Library with this Apify actor. Extract titles, categories, descriptions, prompt content, tags, authors, URLs, and metadata. Supports pagination, keyword filtering, category filtering, deduplication, and exports clean data to JSON, CSV, and Excel.

Biddut Hossain

CLAUDE.md Security Auditor — Scan AI Agent Configs

ianymu/claudemd-security-auditor

claudemd-security-auditor is an Apify Actor that scans any AI agent project's CLAUDE.md, .claude/hooks, and settings for hardcoded secrets, prompt-injection vectors, destructive commands, and exfiltration channels, returning a severity-ranked JSON + Markdown audit.

Yanlong Mu

Semgrep MCP Server

constant_quadruped/semgrep-mcp-server

Cloud-deployed Semgrep static analysis for AI agents. Scan code for security vulnerabilities (SQL injection, XSS, command injection), detect OWASP Top 10 & CWE issues, run custom rules. Supports 30+ languages via MCP.