Agentic Third-Party Risk
33% of enterprise software will be agentic by 2028. 40% of those projects will be canceled due to governance failures. A risk overview for CTOs.
The adoption curve
33% of enterprise software will include agentic AI by 2028 (Gartner). These agents use third-party skills, MCP servers, and tool integrations that most security teams have no process for vetting.
Three risk categories
Skill supply chain: 36.82% of agent skills have vulnerabilities. Protocol security: 7.2% of MCP servers are exploitable. Agent-to-agent trust: multi-agent systems enable 58-90% arbitrary code execution success rates.
What CTOs need to know about agentic third-party risk
33% of enterprise software will include agentic AI by 2028, up from less than 1% in 2024 (Gartner). These agents use third-party skills, MCP servers, and tool integrations that most security teams have no process for vetting. 40% of agentic AI projects will be canceled by end of 2027 due to inadequate risk controls (Gartner). See agent governance for compliance frameworks.
Traditional vendor risk management evaluates software as a static artifact. Agentic third-party risk evaluates behavior: what an agent does with the tools you gave it, how it interacts with external services, and whether its outputs are safe to merge. This is a new risk category that existing security controls do not cover.
Three risk categories
Skill supply chain
36.82% of 3,984 agent skills have known vulnerabilities. 13.4% have critical issues including credential theft and data exfiltration (Snyk ToxicSkills, Feb 2026). See building secure skills.
Protocol security (MCP)
7.2% of 1,899 open-source MCP servers contain vulnerabilities. 5.5% exhibit tool poisoning. 85%+ of identified attacks compromise at least one platform. See MCP security.
Agent-to-agent trust
Multi-agent systems enable 58-90% success rates for arbitrary code execution. Some configurations reach 100% (arXiv:2503.12188). See agent attack landscape.
What traditional VRM misses
Traditional SAST/DAST
Finds code vulnerabilities in static artifacts
Traditional SCA
Finds dependency vulnerabilities in package manifests
XOR
Evaluates agent behavior: what the agent does with its tools, how skills interact, whether the output is safe to merge
Gap
No existing tool evaluates runtime agent behavior against third-party skill integrity
Key stats from published research
36.82%
Agent skills with any security flaw (of 3,984 audited)
Snyk ToxicSkills
85%+
MCP attacks compromising at least one platform
MCPSecBench
20%
Jailbreak success rate across 2,000+ LLM apps
Pillar Security
92%
AI vendors claiming broad data usage rights
Stanford CodeX
[NEXT STEPS]
Deep-dive pages
FAQ
What is agentic third-party risk?
AI agents use external tools, MCP servers, and skills with real permissions. 36.82% of agent skills have vulnerabilities (Snyk ToxicSkills, 3,984 audited, Feb 2026). Traditional vendor risk management doesn't evaluate agent behavior.
How fast is agentic AI adoption growing?
33% of enterprise software will include agentic AI by 2028, up from less than 1% in 2024 (Gartner). 40% of agentic AI projects will be canceled by end of 2027 due to inadequate risk controls.
How does XOR address third-party agent risk?
XOR verifies agent behavior, not just agent code. The platform scans skills for vulnerabilities, checks MCP server integrity, and produces signed compliance evidence for every triage.
MCP Server Security
17 attack types across 4 surfaces. 7.2% of 1,899 open-source MCP servers contain vulnerabilities. Technical deep-dive with defense controls.
Open source supply chain risk index
Composite risk ranking of 200 open source projects by ecosystem importance, supply chain risk, downstream reach, and structural context. 585,601 projects scored.
OWASP Top 10 for Agentic Applications
The OWASP Agentic Top 10 mapped to real-world attack data and XOR capabilities. A reference page for security teams.
How Verification Works
Test agents on real vulnerabilities before shipping fixes.
Automated Vulnerability Patching
AI agents generate fixes for known CVEs. XOR verifies each fix against the vulnerability before it ships.
Benchmark Results
62.7% pass rate. $2.64 per fix. Real data from 1,920 evaluations.
See which agents produce fixes that work
128 CVEs. 15 agents. 1,920 evaluations. Agents learn from every run.