The finale of our OWASP Agentic Skills Top 10 series. AST09: one-line skill installs that no inventory, IAM system, or SOC ever sees — 800+ malicious skills circulating, 83% of organizations deploying agentic AI, 29% ready. AST10: porting skills across platforms silently drops manifests, permissions, and risk tiers. With the Bilateral Receipt Pattern, EU AI Act Article 12, and the Universal Skill Format proposal.
The two post-deployment risks in the OWASP Agentic Skills Top 10: AST07 malicious updates riding channels with no signatures, pinning or freeze mode (40,000 exposed instances in 24 hours), and AST08 scanners that structurally lag base64, zero-width, pure-natural-language and .pyc evasion. Digest pinning, PASS/FAIL/INCOMPLETE pipelines, and Unicode strip ranges — dissected.
Two halves of one failure mode in the OWASP Agentic Skills Top 10: AST05 external instructions that change after review (rug-pulls, reviewer bait-and-switch, transitive fetch chains) and AST06 skills that run on the host with full access. 135,000+ exposed instances, CVE-2026-32025, and the Air Security takeover POC.
AST04 of the OWASP Agentic Skills Top 10: skill metadata is attacker-controlled input - brand impersonation, permission understating, risk-tier spoofing, invisible-character injections, and YAML !!python/object deserialization that executes code at parse time, before approval. Safe-parser and schema controls explained.
AST03 of the OWASP Agentic Skills Top 10: the risk where nothing is malicious and the damage still lands. Permission checks fire at tool-call level, not intent - so a SELECT-permitted skill can DROP TABLE. With Meta's inbox-deletion incident, LPCI and LAAF research, and the per-skill credential controls that close the gap.
AST02 of the OWASP Agentic Skills Top 10 maps attacks on the skill distribution layer: registry flooding, dependency confusion, config files that execute on clone (CVE-2025-59536, CVE-2026-21852), and maintainer takeover. With Trail of Bits' evidence that every marketplace scanner can be bypassed.
AST01 of the OWASP Agentic Skills Top 10 dissected: how ClawHavoc shipped 1,184 malicious skills from 12 accounts, why five of ClawHub's top seven downloads were malware, and how three lines of markdown exfiltrated SSH keys - with the full attack playbook and controls.
The OWASP Agentic Skills Top 10 maps the 10 risks of the AI-agent skill ecosystem - malicious skills, supply chain compromise, over-privileged manifests, metadata attacks, weak isolation, update drift, scanning gaps, governance failures and cross-platform reuse - with real 2026 evidence.
RAG pipelines trust whatever lands in the vector database. Learn how corpus poisoning, retriever manipulation, and injected documents hijack AI answers — and the defenses that actually work in 2026.
How attackers hijack AI applications with nothing but text: direct vs indirect injection, real incidents from Bing to EchoLeak, why no complete fix exists, and the layered architecture that actually contains it.
Five years ago, application security meant securing APIs, patching web frameworks, and hunting for SQL injection in input fields. Today, we’re handing over SSH keys, database credentials, and deployment pipelines to AI agents that make their own decisions about what code to run. Post-Quantum Cryptography for Cyber Professionals Red Teaming LLM Applications: A Practical Playbook […]
Your IAM system answers 'who has access' — AI agents ask 'what will this identity do next.' The authority gap, three real attack scenarios, and a four-layer framework to close it.