Results for “prompt”

Analyzes prompt injection, retrieval poisoning, memory contamination, planner drift, and tool-boundary abuse in agentic systems, mapping trust boundaries and proving exploit chains.

Scans agent skills for security issues including prompt injection, malicious scripts, excessive permissions, secret exposure, and supply chain risks.

Detect prompt injections and jailbreak attempts in LLM applications using Meta's 86M parameter classifier. Filter user inputs, third-party data, and RAG documents with low latency and multilingual support.

Specialized CTF sandbox skill for analyzing prompt-to-tool chains, deployment drift, and supply-chain provenance in cloud, container, and CI/CD environments.

Assess AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, and agent tool abuse, with MITRE ATLAS mapping and guardrail recommendations.

Assigns behavioral trust grades (A–F) to MCP servers by running probes for prompt injection, permission overreach, data leaks, and adversarial-input handling, and publishes reproducible onchain attestations.

Deploy Llama Guard, NeMo Guardrails, and LLM Guard as runtime input/output scanners to block jailbreaks, prompt injection, and toxic content in production LLM applications.

Conduct authorized security assessments of LLM applications and AI agents, covering prompt injection, tool abuse, RAG exposure, memory poisoning, and model supply-chain risks.

Run NVIDIA garak probe suites against an LLM endpoint to test for jailbreaks, prompt injection, data leakage, and toxic generation, then interpret the hit-rate report for triage and reporting.

Builds input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs using NeMo Guardrails, Presidio, and Guardrails AI.

Scans AI agents, MCP servers, and skills for security vulnerabilities from the command line, detecting prompt injections, tool poisoning, toxic flows, malware payloads, and credential handling issues across 15+ risk categories.

Audit installed SKILL.md files and companion scripts for shell injection, secret exfiltration, path traversal, prompt-override payloads, destructive commands, and obfuscation. Integrates with Bankr Safety Scores and produces delta reports against prior scans.

Bypasses safety filters on API-served LLMs using jailbreak templates, input obfuscation, and multi-model racing.

Audit Claude Code configuration files for security vulnerabilities, misconfigurations, and injection risks using AgentShield.

Create and manage Hookify rules that define patterns to watch for and messages to display when those patterns match.

Blocks dangerous shell commands and warns on risky ones, applying a safety protocol before executing any command.

Generates custom safety policies for NVIDIA Nemotron content-safety guardrails, producing a Markdown policy, JSON taxonomy, and inference prompts from rough user input.

Apply least-privilege tool allowlisting, identity binding, and human-in-the-loop controls for agent tool calls.

Scan and audit AI agent skills for security risks before installation, producing a PASS/WARN/FAIL verdict with findings and remediation guidance.

Audits Claude Code configuration files for security vulnerabilities, misconfigurations, and injection risks using AgentShield, covering CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.

Intelligent pattern selection for Fabric CLI. Automatically selects the right pattern from 242+ specialized prompts based on your intent - threat modeling, analysis, summarization, content creation, extraction, and more. USE WHEN processing content, analyzing data, creating summaries, threat modeling, or transforming text.

Scans local repos and AI agent skill folders for security drift, saves trusted baselines, and compares changes after updates to highlight risky new capabilities.

Store and retrieve API keys, passwords, and credentials in an HSM-backed encrypted vault via MCP or REST API, with policy-based access control, secret rotation, multi-chain signing, and prompt injection scanning.

Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations, detecting attack vectors where attacker-controlled input reaches AI agents in CI/CD pipelines.

Audit App Store and Google Play listings for discoverability and conversion — keywords, localized metadata, screenshots, ratings prompts — then emit a prioritized ASO plan. Use when "optimize our store listing", "improve app downloads", or "ASO". Submission mechanics → plan-mobile-readiness. Plan only.

Automate multi-turn adversarial conversations against LLM agents using Microsoft PyRIT, including Crescendo and Tree-of-Attacks-with-Pruning (TAP) attack chains with scorer feedback loops.

Performs interactive dynamic malware analysis using the ANY.RUN cloud sandbox to observe real-time execution behavior, interact with malware prompts, and capture process trees, network traffic, and system changes.

Migrates symbols and reverse-engineering results from an older binary version to a newer one using LLM-based structured diffing of disassembly and pseudocode, enabling rapid offset and function-name mapping when PDBs are missing.

Composite skill — first-touch workflow for an unfamiliar repo. Chains adt-repo-intake (understand) → audit-deep (health check) → config-drift-detect (gate audit) → init (CLAUDE.md if missing) → fewer-permission-prompts (prune permission noise). Use when entering a new repo for the first time, taking over from another developer, or after a major repo restructure.

This skill should be used when establishing comprehensive QA testing processes for any software project. Use when creating test strategies, writing test cases following Google Testing Standards, executing test plans, tracking bugs with P0-P4 classification, calculating quality metrics, or generating progress reports. Includes autonomous execution capability via master prompts and complete documentation templates for third-party QA team handoffs. Implements OWASP security testing and achieves 90% coverage targets.