LLM prompt injection via permissive URL prefix matching
Published Jul 16, 2026 · Updated Jul 16, 2026
Improper URL validation in Apify MCP Server before 0.9.21 allows remote attackers to inject LLM content through crafted URLs. The fetch-apify-docs tool tests a raw URL with String.startsWith against documentation prefixes, then fetches and returns attacker-hosted HTML as markdown. Exploitation requires a user or connected agent to invoke the tool with the crafted URL; the returned content can direct the LLM and manipulate subsequent tool actions.
Summary
What happened
Improper URL validation in Apify MCP Server before 0.9.21 allows remote attackers to inject LLM content through crafted URLs. The fetch-apify-docs tool tests a raw URL with String.startsWith against documentation prefixes, then fetches and returns attacker-hosted HTML as markdown. Exploitation requires a user or connected agent to invoke the tool with the crafted URL; the returned content can direct the LLM and manipulate subsequent tool actions.
The record
- CVE
- CVE-2026-46341
- Published
- Jul 16, 2026
- Updated
- Jul 16, 2026
- Vendor
- Apify
- Product
- Apify MCP Server
- Classifications
- CWE-183, CWE-20, T1204.001
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jul 16, 2026CVE publishedPublication date reported by the CVE source.
- Jul 16, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 0.9.21
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- GHSA-jwp7-wg77-3w9v crafted tools/call requestproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo