Results for “insider-threat”

Scan untrusted external text (web pages, tweets, search results, API responses) for prompt injection attacks. Returns severity levels and alerts on dangerous content. Use BEFORE processing any text from untrusted sources.

Detect and defend against prompt injection hidden in documents, web pages, and images consumed by an agent.

Threat-model and harden AI agents, RAG systems, assistants, and tool-using workflows against direct, indirect, stored, cross-agent, and multimodal prompt injection. Use when reviewing an agent architecture, isolating untrusted content, constraining tools and egress, protecting secrets, adding injection-focused tests, investigating a suspected injection incident, or documenting residual prompt-injection risk.

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

Security audit orchestrator for agent skills — scans for prompt injection, data exfiltration, credential theft, supply chain risks, and instruction hierarchy violations before any skill is installed, created, improved, or read from a GitHub repo. Load when creating skills from external sources, when improve-skills reads from GitHub repos, when research-skill fetches community SKILL.md files, when a user installs a third-party skill, or when the user asks to audit skill security, scan for injection, check if a skill is safe, scan all skills, or run a security sweep. Orchestrates all secure-* skills in sequence. Content is SAFE only if ALL secure-* skills return SAFE. 36% of community skills contain flaws (Snyk ToxicSkills 2026). This skill is the first line of defense.

Read-only OWASP LLM Top 10 audit of app-facing AI features: prompt injection, data leak, supply chain, poisoning, unsafe output, excessive agency, system-prompt leak, RAG/embedding risks, misinformation, unbounded consumption. Use when "audit LLM security", "prompt injection", "jailbreak my chatbot", "is my AI safe".

Execute and analyze AI Data Poisoning attacks. By subtly injecting malicious or targeted misinformation into an LLM's training or fine-tuning dataset, an attacker can covertly manipulate the model's future outputs, implant backdoors, or enforce biases without altering the model architecture.

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

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.

Models threats for a service, feature, endpoint, integration, or architecture: assets, attackers, boundaries, flows, and abuse cases.

Model threat actors, intrusion sets, campaigns, and TTPs as a STIX 2.1 knowledge graph in OpenCTI using the pycti Python client, connectors, and import workers for structured cyber threat intelligence.

Drafts and sequences internal change-management communications (re-orgs, layoffs, policy changes) using ADKAR and Kotter models, producing announcement text, FAQ, manager talking points, and a touchpoint calendar.

Test vector stores for embedding inversion, cross-tenant leakage, and poisoning.

STRIDE Threat Model

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

Review docs, tool output, skills, and memory candidates for prompt-injection risk.

AIDefence security layer with prompt injection blocking, input validation, sandboxed execution, output sanitization, and STRIDE threat modeling.

Designing red team attack scenarios, threat models, MITRE ATT&CK/OWASP application, Purple Team exercises, and AI/LLM red teaming. Use when adversarial security validation is needed.

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.

Detect poisoned training data and backdoored models across the ML pipeline using statistical analysis, activation clustering, and spectral signatures.