All projects matching “detect prompt injection”

Prompt-Guard Zero-Trust LLM Jailbreak & Injection Shield: Detects indirect prompt injection, jailbreaks, and tool-poisoning payloads in untrusted inputs.

Payment security firewall scan for an OUTGOING x402 payment: PII/secret leak detection in payment metadata, nonce replay detection, overpayment detection, prompt-injection-triggered payment analysis (fast + deep tiers), canonical-USDC asset verification, merchant pinning, velocity/spend caps, and counterparty reputation cross-check. Returns allow/flag/block with per-check reasons and an Ed25519-si

AI Security Guard content scanner. Detects prompt injection, intent drift, and credential exfiltration. $0.0015-$0.024 by size. Full docs: https://aisecurityguard.io/v1/skill

Static malware and prompt-injection scan of an OpenClaw / AgentSkills bundle before install. Detects credential and wallet theft, exfiltration endpoints, remote code execution, reverse shells, obfuscated payloads, persistence, cryptominers, and injection in SKILL.md. Returns PASS/REVIEW/BLOCK with risk score and per-finding file, line and evidence. bundle = {files:[{path,content}]} or {github:'own

Prompt-injection scan for text your AI agent is about to read (web pages, emails, tool output, MCP tool descriptions): risk score 0-100, verdict, categories and exact spans. Detects instruction overrides, jailbreak personas, system-prompt extraction, fake chat delimiters, data-exfiltration URLs, tool hijacking, hidden Unicode and encoded payloads. Deterministic rules, no data stored.

Deterministic prompt-injection firewall and honeypot scrubber for AI agents. Sanitizes untrusted text and blocks detected wallet-draining commands before context ingestion.

Statically analyse a Model Context Protocol (MCP) server manifest for security risks. Tool descriptions enter the model context, a prime prompt-injection vector. Deterministic and offline (inline manifest). Flags dangerous capabilities (command/code execution, filesystem, credential and network access), injection patterns, hidden unicode and unconstrained parameters. Returns severity-ranked findin