16 skills · sorted by relevance
Review source code for MCP, a protocol connecting AI applications to tools. Check authentication, input validation, unsafe execution, and other security risks, then report findings with file and line references and separate manual follow-ups.
Screen AI application inputs and historical logs for prompt injection, where malicious instructions try to redirect the model. Combine pattern matching, text structure scoring, and a DeBERTa classifier to flag suspicious content and produce JSON results.
Validate and constrain untrusted input at the boundary. Use on any handler that accepts external data.
The English summary is being prepared. Showing the original description.
Validate construction data inputs before processing: cost estimates, schedules, BIM data, field reports. Catch errors early with domain-specific rules.
The English summary is being prepared. Showing the original description.
Validate and sanitize all API inputs. Zod schemas, error responses, security considerations.
The English summary is being prepared. Showing the original description.
Detects prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The detector analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-based escapes). Based on the OWASP LLM Top 10 (LLM01:2025 Prompt Injection) and Simon Willison's prompt injection taxonomy. Activates for requests involving prompt injection detection, LLM input sanitization, AI security scanning, or prompt attack classification.
The English summary is being prepared. Showing the original description.
Senior Kotlin specialist code review — framework-agnostic. Use whenever the user asks to review, audit, critique, or get feedback on Kotlin code, a file, a class, a function, a module, a diff, a branch, a commit, or a pull request. Judges Kotlin language idioms, logic correctness, architecture and layering, concurrency (coroutines, Flow, structured concurrency, cancellation, race conditions), null safety, exception safety, testability, performance, and security. Detects force-unwraps, unchecked casts, GlobalScope, leaked mutability, broken structured concurrency, hidden side effects, weak abstractions, untestable seams, allocation hot spots, weak crypto, input-validation gaps, and PII logging. Outputs prioritized findings with file:line anchors and minimal-diff fixes. No assumptions about DI framework, UI framework, or build system.
The English summary is being prepared. Showing the original description.
Validate UI, command, text, numeric, entity, and configuration input with localized feedback and server authority.
The English summary is being prepared. Showing the original description.
Implement API schema validation using OpenAPI specifications and JSON Schema to enforce input/output contracts and prevent injection, data exposure, and mass assignment attacks.
The English summary is being prepared. Showing the original description.
tespit etme (s) prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The tespit etme (or) analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-...
The English summary is being prepared. Showing the original description.
Implements input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs. Builds a security validation pipeline using NVIDIA NeMo Guardrails Colang definitions, custom Python validators for PII Tespit and content policy enforcement, and the Guardrails AI framework for structured output validation. The guardrails system intercepts both user inputs (blocking injection attempts, stripping PII, ...
The English summary is being prepared. Showing the original description.
Security-Scanner Agent fuer fabrikIQ und andere Projekte. Fuehrt umfassende Sicherheitspruefungen durch. Trigger bei: (1) Pre-commit Validation, (2) PR-Creation, (3) Weekly Security Audits, (4) Nach Dependency-Updates, (5) Vor Production Deployments. <example> Context: User moechte vor einem Commit sicherstellen, dass keine Secrets committed werden. user: "Ich will gleich committen. Pruefe mal auf Secrets." assistant: "Ich starte den security-scanner Agent, um den Code auf API Keys, Tokens und andere Secrets zu pruefen." <Task tool call to security-scanner agent> </example> <example> Context: Weekly Security Audit des fabrikIQ-Projekts. user: "Fuehre den woechentlichen Security-Scan durch." assistant: "Ich fuehre einen vollstaendigen Security-Scan durch: Secret Detection, Dependency Audit, OWASP Patterns, Security Headers und Rate Limiting." <Task tool call to security-scanner agent> </example> <example> Context: User hat Dependencies aktualisiert und will Vulnerabilities pruefen. user: "Ich habe npm update und pip install -U gemacht. Gibt es Sicherheitsprobleme?" assistant: "Ich scanne die aktualisierten Dependencies auf bekannte Vulnerabilities mit dem security-scanner Agent." <Task tool call to security-scanner agent> </example> <example> Context: PR-Review mit Security-Fokus. user: "Review den PR #42 auf Security-Probleme." assistant: "Ich analysiere die geaenderten Dateien im PR auf Security-Patterns: SQL Injection, XSS, Hardcoded Credentials und fehlende Input-Validation." <Task tool call to security-scanner agent> </example>
The English summary is being prepared. Showing the original description.
Detects prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The detector analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-based escapes). Based on the OWASP LLM Top 10 (LLM01:2025 Prompt Injection) and Simon Willison's prompt injection taxonomy. Activates for requests involving prompt injection detection, LLM input sanitization, AI security scanning, or prompt attack classification.
The English summary is being prepared. Showing the original description.
Validates HTTP request inputs. .NET 10 AddValidation, FluentValidation, ProblemDetails.
The English summary is being prepared. Showing the original description.
Detects prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The detector analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-based escapes). Based on the OWASP LLM Top 10 (LLM01:2025 Prompt Injection) and Simon Willison's prompt injection taxonomy. Activates for requests involving prompt injection detection, LLM input sanitization, AI security scanning, or prompt attack classification.
The English summary is being prepared. Showing the original description.
Identifies and fixes XSS, SQL injection, and command injection vulnerabilities with validation schemas, sanitization libraries, and safe coding patterns. Use for "input validation", "XSS prevention", "SQL injection", or "sanitization".
The English summary is being prepared. Showing the original description.