Agentjacking Turns MCP Tool Output Into an Execution Path
Tenet's Agentjacking research shows how fake Sentry errors can hijack coding agents through MCP tool output. The defense starts with treating tool data as untrusted.
#prompt-injection
4 articles with this tag.
Agent Phishing Shows Why Tool Permissions Need Identity Checks
Varonis and Imperva showed OpenClaw agents leaking data and running code from ordinary-looking inputs. The defense starts with identity-bound tool permissions.
ToxicSkills: What the First Large-Scale Agent Skill Audit Found
Snyk scanned 3,984 AI agent skills: 36% had security flaws, 534 critical issues, 76 active malware. What this means for developers installing skills.
MCP Tool Poisoning: How Hidden Metadata Hijacks AI Agents
MCP tool descriptions are visible to your AI agent but hidden from you. Attackers embed instructions that hijack agent behavior and steal credentials.