Security

Prompt Guard: Evaluation & Security Prompt Guard is an intelligent AI agent that evaluates, strengthens, and secures prompts before deployment. It identifies ambiguities, detects PII or injection risks, flags bias and compliance gaps, and predicts output consistency. Each evaluation provides scores, rationales, and three optimized versions (Streamlined, Hardened, High-Impact), with smart revision tools, sentiment checks, and automated redaction. Prompt Guard empowers AI developers and organizations to deploy safe, high-performing, and compliant prompts—fast, measurable, and secure. Built for the *Liam Ottley × AAA Accelerator Hackathon.* 📘 User Guide & Technical Documentation ▶️ Demo

PII Governance Agent - Automated Privacy Protection for Enterprise AI Protect sensitive data with intelligent, real-time PII detection and remediation. Capabilities: • Mask sensitive data during processing • Redact PII from outputs • Highlight risks for human review • Log instances for audit trails Deploy standalone or integrate into multi-agent systems across distributed environments. Dual-Mode Operation: Cost-Effective: Fast detection using code-based rules for high-volume operations. LLM-Enhanced: Advanced contextual analysis catching nuanced PII patterns traditional methods miss. Meet regulatory compliance while maintaining operational efficiency.

Supports managers in reviewing the overall code quality with evidence based feedback. Assess maintainability, security and performance of GitHub pull requests by user and provides actionable feedback. Managers can manually override and validate quality scores given in Knowledge Tables where the detailed feedback is stored by direct report. The agent will manager validated scores to self improve assessments.

An expert security consultant that helps organizations create comprehensive, compliant security policies and procedures. Specializes in drafting policies for information security, data protection, incident response, access control, and regulatory compliance frameworks like ISO 27001, SOC 2, GDPR, and HIPAA.

Runs non destructive OWASP Top 10 HTTP requests against deployed web applications as a DAST. Reads Open API Specs, saves the schema to knowledge and crafts HTTP requests for OWASP Top 10 issues. Generates a report of potential vulnerabilities on endpoints.

CPG – Compliance Advisory Assistant is an AI-powered advisor purpose-built for regulated and security-focused organizations that need clarity—not noise—when navigating complex compliance requirements. CPG does not directly connect to production systems, monitor environments in real time, or autonomously enforce controls. Instead, it operates strictly on the information provided by users or integrated systems, such as: exported logs configuration reports policy documents workflow descriptions audit findings cloud scan outputs from invoked tools With these inputs, CPG specializes in: 1. Regulatory & Policy Interpretation CPG interprets dense compliance frameworks—GDPR, HIPAA, PCI-DSS, ISO 27001, SOC 2, SOX—alongside internal policies to translate legal and technical requirements into precise, actionable guidance. 2. Evidence-Based Compliance Analysis Given logs, reports, or tool outputs, CPG identifies: potential compliance violations configuration weaknesses policy misalignments operational control gaps Every finding is tied to recognized standards and includes severity, impact, and remediation guidance. 3. Documentation & Audit-Readiness Support CPG generates: audit-ready reports compliance scorecards incident summaries remediation plans gap analyses control descriptions These outputs help teams prepare for audits and strengthen internal governance. 4. Practical, Plain-Language Compliance Guidance Instead of theoretical advice, CPG maps high-level regulatory language to real-world operational requirements—helping security teams, compliance officers, risk managers, and auditors understand exactly what must be done to stay compliant. ⚠️ Disclaimer CPG is an automated compliance advisory tool intended for informational guidance only. It does not provide legal advice. Organizations should consult qualified legal counsel for decisions involving legal interpretation, risk management strategies, or regulatory obligations.

Re Dactyl identifies and removes specified types of sensitive or inappropriate content from text, including PII, sensitive information, NSFW text, and hostile language, based on the agent's prompt configuration.