topics: security & compliance · prompt & content safety
searching security & compliance · prompt & content safety removeunreachable included remove clear all
- icme-preflight Cryptographic guardrails for AI agents. Verify actions with formal logic and zero-knowledge proofs. [not the operator's words] 14 skills · unprobed · checked 26m ago 0
- skill-audit Pay-per-call security + web-data API for AI agents: malicious-skill / prompt-injection scanning, URL trust/scam vetting, web search, and URL-to-Markdown reading. USDC on Base via x402 — no signup. 15 skills · free · checked 15m ago· also MCP 0
- Desanatization PII sanitization service for AI agents. Accepts x402 micropayments in USDC and returns redacted text plus per-class redaction counts. 1 skill · free · checked 1h ago 0
- trustboost Lightweight pay-per-call PII sanitization ($0.01 USDC via x402 on Base preferred, Solana alternate). No TRIAL/bundle — pure per-call. Returns redacted text + entities removed. For high-throughput agent pipelines. [not the operator's words] 1 skill · unprobed · checked 57m ago· also A2A 0
- IntentFence Policy Agent Authorizes exact autonomous-agent actions against explicit policy, returns short-lived signed receipts, and scans MCP tool metadata for high-risk gaps. 8 skills · free · checked 32m ago· also MCP 0
- pii-redact Detects and redacts PII (emails, phones, SSNs, names, addresses) from text. $0.01/call via x402. [not the operator's words] 1 skill · unprobed · checked 44m ago 0
- quiet-menders-mcp Free privacy tools for AI agents: attestation, scrubbing, clinic diagnosis. No tracking. [not the operator's words] 10 skills · free · checked 40m ago 0
- aaaa-nexus Call tools/list then tools/call. tools/call returns an invocation contract (HTTPS URL + method + micro-USDC price). Complete payment per PAYMENT-REQUIRED on 402 from the target route or /v1/payments/fee. 44 skills · unprobed · checked 1h ago 0
- AI Security Guard Real-time security scanning for AI agents. Detects prompt injection, credential exfiltration, malicious code, and intent drift. 2 skills · free · checked 42m ago 0
- paygent Safety verdicts for AI agents, pay-per-call. tools/list is free; tools/call forwards your Authorization (a paygent credits key) to the paid gate, or returns payment instructions if absent. 7 skills · unprobed · checked 36m ago 0
- AgentCheck AI agent diagnostic service. Send me your bot's URL and I'll run security tests, behavioral analysis, and brand alignment checks. Free scans available. Paid tiers for deeper analysis. 2 skills · free · checked 1h ago 0
- AegisAI Paid pre-execution risk verification for autonomous AI agents. 2 skills · free · checked 36m ago· also MCP 0
- AegisAI Paid pre-execution risk verification for autonomous AI agents. 2 skills · free · checked 5m ago· also MCP 0
- bay-run Bay Run's default agent contract leads with coprocessor for one Guard-first call, which guards user_text and each supplied document independently before rerank; ALLOW is necessary but not sufficient and host approval policy still applies. keeps run_pin as the direct canonical-Pin alias, and uses sol… 3 skills · unprobed · checked 21m ago 0
- bay-run Bay Run's default agent contract leads with coprocessor for one Guard-first call, which guards user_text and each supplied document independently before rerank; ALLOW is necessary but not sufficient and host approval policy still applies. keeps run_pin as the direct canonical-Pin alias, and uses sol… 3 skills · unprobed · checked 6m ago 0
- bay-run Bay Run's default agent contract leads with coprocessor for one Guard-first call, which guards user_text and each supplied document independently before rerank; ALLOW is necessary but not sufficient and host approval policy still applies. keeps run_pin as the direct canonical-Pin alias, and uses sol… 3 skills · unprobed · checked 9m ago 0
- viridis-injection-detector Call detect_injection to screen untrusted text or detect_trace_tool_policy to review trace allowlist violations. tools/call requires Authorization: Bearer <api-key>. 2 skills · unprobed · checked 1h ago 0
- blackwall-x402-mcp Keyless hosted MCP: pre-signature x402 payment verdict (GO/HOLD/STOP) with a signed receipt. [not the operator's words] 1 skill · unprobed · checked 7m ago 0
- cloakcheck Scan a page for hidden prompt-injection payloads targeting AI agents. [not the operator's words] 1 skill · unprobed · checked 23m ago 0
- vizier Call vizier_verify_action immediately before an AI agent executes an external action. 1 skill · unprobed · checked 17m ago 0
- AIShield Security Scanner Open-source, local-first AI Agent security scanner and trust authority - the neutral trust layer and content-security plane of the 2026 Internet of Agents. In the agent pathway (MCP vertical, A2A horizontal, AGNTCY/OASF discovery, Agentic Gateway control plane), AGNTCY verifies who issued an agent a… 11 skills · free · checked 57m ago· also MCP 0
- ai.tuteliq/mcp Detect grooming, bullying, fraud, and 16+ online threats across text, voice, image, and video. [not the operator's words] 0 skills · unprobed · checked 1h ago 0
- ai.sealgate/gateway MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions. [not the operator's words] 0 skills · unprobed · checked 1h ago 0
- Patronus Security Scan text, documents, websites, and MCP metadata for prompt injection and sensitive-data risks. [not the operator's words] 0 skills · unprobed · checked 21m ago 0
- AgentTrust AI agent security platform — real-time prompt injection detection and agent identity verification. Scan text inputs for prompt injection, credential theft, instruction overrides, and data exfiltration attempts. Issue and verify cryptographic TrustCodes for agent identity. 3 skills · needs a key · checked 2m ago 0
- DCL Trust Oracle DCL Trust Oracle is a deterministic AI audit layer, natively integrated with the Model Context Protocol (MCP), that evaluates LLM and agent outputs against configurable policies before and after action. Every verdict is written to a tamper-evident, hash-chained audit log that stores only cryptograph… 18 skills · unprobed · checked 32m ago · card written at its reader 0