TL;DR: Hallucinated packages showed up in 5.2% of commercial-model outputs and 21.7% of open-source-model outputs, Orca Security reports, with more than 205,000 unique fake package names identified. Reachability analysis has to sort exploit-ready code from noisy findings if teams want remediation to reflect real production exposure.
Editorial analysis by NHI Mgmt Group, based on content published by Orca Security: “Best AI Code Security Solutions 2026: How to Secure AI-Generated Code”.
By the numbers:
- Hallucinated packages appeared in at least 5.2% of commercial-model outputs and 21.7% of open-source-model outputs in a USENIX Security 2025 study cited by Orca Security.
Key questions
Q: Why do package hallucinations and dependency confusion increase supply chain risk?
A: They exploit trust in automation.
Q: What are the signs that AI code security tooling is too noisy?
A: The main signs are large alert volumes, weak differentiation between exploitable and unreachable code, and remediation effort spent on findings that never reach production.
A: Security teams should prioritise findings by business exposure, not just technical severity.
Practitioner guidance
- Prioritise reachable findings first Rank AI-generated code issues by whether the vulnerable path is actually executed in production and whether it touches exposed workloads or sensitive data.
- Verify every generated dependency Require package existence checks, publisher validation, and dependency pinning before any model-suggested import is accepted into the build pipeline.
- Scan secrets at commit and pull request time Look for API keys, tokens, and other credentials in code, history, and PR diffs, then revoke anything that reaches a shared branch.
Bottom line: AI-generated code introduces a distinct risk profile because insecure patterns, invented dependencies, and exposed secrets can appear at scale even when the code looks plausible.
Glossary terms: AI Code Security, Reachability analysis, Slopsquatting, Code-to-Cloud Context
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
Reachability is becoming the new control boundary for AI code security. AI-generated code expands the volume of findings, but only a subset of those findings are actually exploitable in the running environment. That changes the governance model from inventorying every defect to proving whether a defect can reach live data or live execution. The implication is that AppSec teams must treat exploit path as the unit of priority, not the alert itself.
A few things that frame the scale:
- AI-related credential leaks surged 81.5% year-over-year in 2025, with the surrounding AI infrastructure leaking 5x faster than core LLM providers, according to the State of Secrets Sprawl 2026.
A question worth separating out:
Q: How should security teams govern AI-generated code in production environments?
A: Security teams should treat AI-generated code as normal production code with extra provenance risk. Require architectural review, test coverage, static analysis, and approval before merge. Then bind the agent and the build pipeline to least privilege, short-lived credentials, and complete audit logging so implementation speed does not outrun control.
👉 Read our full editorial: AI code security now hinges on reachability, not severity