Results for “prompt-injection-defense”

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

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

Probe RAG applications for prompt injection via poisoned retrieved context and embedding manipulation.

Detects prompt injection attacks targeting LLM-based applications using regex pattern matching, heuristic scoring, and DeBERTa transformer classification.

Add safety guardrails to an LLM app — prompt-injection defense, output validation, PII handling, and a clear refusal policy.

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.

Wire Promptfoo and DeepTeam into CI/CD for automated regression red-teaming of LLM apps against OWASP LLM Top 10 and OWASP Agentic presets, failing the build when jailbreak or injection vulnerabilities regress.

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 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.

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.

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

Learn and apply prompt engineering techniques for LLMs, image generators, and video models using the inference.sh CLI.

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

Agent profile for review prompt injection, tool boundaries, untrusted content, data exfiltration, and human approval gates. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.

Full specialist analysis via parallel agent dispatch. Researcher, Architect, and PM produce a prioritized report of what to build next (30-60s).

Optimize prompts via process goals (controllable behavioral instructions) rather than outcome goals (sparse end-result demands). Grounded in sports psychology meta-analysis showing process goals (d=1.36) vastly outperform outcome goals (d=0.09). Use when designing prompts, optimizing LLM steering, implementing CoT/decomposition patterns, or building automatic prompt optimization pipelines. Instantiates surrogate loss paradigm for discrete prompt space.

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.