Notifications
Clear all
Topic starter
05/07/2026 6:45 pm
TL;DR: Prompt injection manipulates LLM instructions to override safeguards, extract sensitive data, and alter model behaviour, according to Lakera’s analysis of direct, indirect, and multilingual attack patterns. The security gap is not just content filtering but governance for what AI systems are allowed to read, trust, and execute at runtime.
NHIMG editorial — based on content published by Lakera: Prompt Injection and the Rise of Prompt Attacks, All You Need to Know
By the numbers:
- Prompt injection is the number one AI security risk in the 2025 OWASP Top 10 for LLMs.
Questions worth separating out
Q: How should security teams defend against prompt injection in AI applications?
A: Use layered controls. Separate system instructions from user input, sanitise retrieved content, require authorisation before tool use, and monitor for abnormal prompt patterns. No single filter is enough because prompt injection is an adaptation game, not a static signature problem. The goal is to prevent model compromise from becoming execution compromise.
Q: Why do AI copilots and agents make prompt injection risk worse?
A: They widen the impact of a successful injection.
Q: What do organisations get wrong about prompt injection?
A: They often treat it as a content moderation problem instead of an access and execution problem.
Practitioner guidance
- Separate trusted instructions from untrusted content Keep system prompts, policy rules, and user-controlled text in distinct layers so attacker text cannot override the governing instruction set.
- Gate tool use behind explicit authorisation Require deterministic permission checks before an AI system can call tools, access records, or trigger workflows.
- Test indirect and multilingual attack paths Red team models using copied text, web retrieval, translated prompts, obfuscation, and context-hijack patterns.
What's in the full article
Lakera's full article covers the operational detail this post intentionally leaves for the source:
- Examples of direct and indirect prompt injection patterns that security teams can test against.
- A fuller breakdown of prompt attacks versus non-prompt attacks for implementation teams.
- Lakera's discussion of runtime detection and multi-layered AI security controls in production environments.
- The article's practical defence checklist for securing AI applications against adversarial prompts.
👉 Read Lakera's analysis of prompt injection and AI prompt attacks →
Prompt injection and AI security controls: what IAM teams miss?
Explore further
05/07/2026 7:01 pm
Prompt injection is a governance problem before it is a model problem. The attack works because organisations have treated model input as text instead of as an access-controlled control plane. Once the model can read external content, internal prompts, or memory without strong boundaries, the security question shifts from content filtering to instruction authority. Practitioners should treat prompt handling as part of identity and access design, not as a cosmetic layer on top of AI.
A few things that frame the scale:
- The average estimated time to remediate a leaked secret is 27 days, despite 75% of organisations expressing strong confidence in their secrets management capabilities, according to The State of Secrets in AppSec.
- 43% of security professionals are concerned about AI systems learning and reproducing sensitive information patterns from codebases, according to The State of Secrets in AppSec.
A question worth separating out:
Q: How can teams reduce the blast radius of a compromised AI prompt?
A: Limit the model’s permissions, isolate sensitive retrieval sources, and require separate checks before any downstream action is taken. If the model cannot reach secrets, production tools, or approval paths by default, a successful injection is far less likely to become an enterprise incident.
👉 Read our full editorial: Prompt injection exposes the identity gap in AI security controls
