Live Exposure Defense: From CVE to Confirmed Exposure in 12 Hours – See more

Back
New CVE Detected

CVE-2026-77255 – Arbitrary File Read & Credential Exfiltration (Confused Deputy) – mcp-atlassian < 0

Be the first to know when new zero-days emerge:

Subscribe to Email Alerts
Subscribe to RSS Feed

Summary

CVE-2026-77255 is a high-severity confused-deputy / path traversal vulnerability (CVSS 8.6) in mcp-atlassian, an open-source Model Context Protocol (MCP) server that connects AI agents to Jira and Confluence. The Jira update_issue tool’s attachments parameter accepts unsanitized file paths, allowing an attacker-controlled AI agent or prompt injection to make the server read arbitrary local files — including process environment variables and credential material — and attach them to a Jira issue, exfiltrating the data outside the host.

Technical details

  • Root cause: The update_issue function processes attachment arguments without validating them against a safe base directory, permitting absolute paths (e.g., /proc/self/environ) and directory traversal sequences (../).
  • Trigger conditions: Any caller able to invoke the update_issue tool with attacker-influenced attachments values — including an AI agent manipulated via prompt injection — can trigger the flaw; no authentication to the underlying host filesystem is required beyond the MCP server’s own Jira session.
  • Attack vector: Network (AV:N) — exploitable through normal MCP tool-call interactions with no user interaction and low complexity (AC:L, UI:N, PR:N).
  • Impact: The MCP server acts as a "confused deputy," reading sensitive host files (system configuration, environment variables containing the server’s own JIRA_API_TOKEN, SSH keys, etc.) and attaching them to a Jira issue where the attacker can retrieve them. Impact is scoped to confidentiality only (C:H/I:N/A:N), but exposed credentials can enable further lateral movement and privilege escalation. The Scope is Changed (S:C) since the impact extends beyond the vulnerable component to the Jira instance and any secrets stored on the host.

Affected software

  • mcp-atlassian (sooperset/mcp-atlassian) — all versions prior to 0.22.0

Severity

  • CVSS v3.1 Base Score: 8.6 (High)
  • Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N

Mitigation and recommended actions

  • Immediate: Upgrade mcp-atlassian to version 0.22.0 or later, which restricts attachment paths and validates them against a safe base directory.
  • If immediate patching is not possible:
    • Restrict or disable the update_issue tool’s attachment functionality for untrusted or agent-driven callers.
    • Run the mcp-atlassian server with the least-privileged filesystem and OS user permissions possible, and avoid storing long-lived credentials in environment variables accessible to the process.
    • Monitor Jira audit logs for issue updates containing unexpected or system-path-named attachments.
    • Limit network exposure of the MCP server and enforce strict input validation/allow-listing on any AI agent or automation pipeline that can invoke MCP tools.

References

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report

How IONIX’s External Exposure Management Platform Detects and Validates
Zero-Days to Shrink MTTR

1

Map your entire attack surface (continously)

IONIX uses multi-factor discovery methods, including DNS analysis, certificate mapping, metadata inspection, and more, to automatically map every internet-facing asset across your environment. This includes cloud instances, third-party platforms, shadow IT, and even forgotten infrastructure that traditional tools miss.

2

Monitor for new CVEs

Dozens of threat intel feeds using agentic technology are continuously analyzed to detect the appearance of proof-of-concept code, exploit kits, and indicators of active targeting. IONIX goes further by applying AI to proactively evaluate whether emerging vulnerabilities are likely to be exploited, even before PoCs go public.

3

Identify Potential External Exposures

Not all CVEs matter. IONIX filters vulnerabilities by asking attacker-centric questions: Can it be reached from the internet? Does it require authentication? Is it being exploited in the wild? This dramatically reduces noise and focuses teams on threats that can actually be weaponized.

4

Create Safe, Scalable Exploit Validations

IONIX transforms real-world PoCs into safe, non-intrusive test payloads that can be run in production environments without disruption. These simulations are precisely targeted to the systems that are vulnerable, ensuring rapid validation without unnecessary load.

5

Execute Exploit Validations

By combining context about software stack, versioning, exposure status, and reachability, IONIX ensures that only the right payloads are executed against the right assets, maximizing efficiency and minimizing risk.

6

Drive Fast and Actionable Remediation

Results are routed through integrations with ticketing, SOAR, and SIEM tools. Issues are written in plain language, bundled into remediation clusters, and prioritized based on asset criticality, exploitability, and blast radius. This shortens mean time to remediation (MTTR) and empowers teams to act with confidence.

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report
Close

Subscribe to Threat Center RSS

Copy/paste the link below into your preferred RSS reader or follow these instructions to subscribe to Slack alerts.

Open RSS feedSlack setup instructions

Close

Get Real-Time CVE Alerts to Your Email

Be the first to know when new zero-days emerge