À PROPOS DE CET ÉPISODE

Anglais
États-Unis

TRANSCRIPTION 🔗

RECHERCHER LES ÉPISODES PASSÉS

Rechercher les épisodes précédents de The Agentic Stack | VekktorAI.

AUTRES ÉPISODES DANS CE PODCAST

Indirect prompt injection is being stress-tested from three directions at once, and the shared assumption underneath current agent security practice is what's under pressure. Three papers published within nine days of each other reframe the problem: ECLIPSE describes a self-evolving attack bui…
Agent skill supply-chain security is where prompt injection is heading next. This week on The Agentic Stack, we work through SkillSecurer, an arXiv preprint submitted on September 12, 2026, that detects and patches prompt injection vulnerabilities inside the reusable capability modules agents load.…
Strands shipped a harness on September 21st, 2026 with a headline claim of frontier performance at 28% lower token cost. Three days later, Dark Reading reported a prompt-injection vulnerability in the agentic app Manus that could have enabled data theft and compromise. This episode connects the har…
Avertissement: Le podcast et les illustrations intégrés sur cette page proviennent de VekktorAI, qui est la propriété de son propriétaire et n'est ni affilié ni approuvé par Listen Notes, Inc.