# MCP Atlassian: JIRA_PROJECTS_FILTER / CONFLUENCE_SPACES_FILTER allow forbidden-project content exfiltration (one LIVE-proven on Atlassian Cloud) Advisory record · `GHSA-w66g-j6c4-hcfc` - **Identifiers:** `GHSA-w66g-j6c4-hcfc` · `CVE-2026-77251` · `PYSEC-2026-4102` - **State:** Confirmed - **Severity:** CVSS 8.3 High - **Critical:** No - **Weakness (CWE):** [CWE-184](https://cwe.mitre.org/data/definitions/184.html) · [CWE-693](https://cwe.mitre.org/data/definitions/693.html) · [CWE-863](https://cwe.mitre.org/data/definitions/863.html) · [CWE-1276](https://cwe.mitre.org/data/definitions/1276.html) - **Tags:** [Broken access control](https://agentprime.io/advisories/tag/access-control.md) · [CWE-184](https://agentprime.io/advisories/tag/cwe-184.md) · [CWE-693](https://agentprime.io/advisories/tag/cwe-693.md) · [CWE-1276](https://agentprime.io/advisories/tag/cwe-1276.md) - **Published:** 22 Sept 2026 - **Updated:** 1 Oct 2026 - **Reviewed by a person:** No Published by the GitHub Advisory Database at 22 Sept 2026, 20:34 UTC. agentprime has not analysed this yet, so whether it affects any app is not known. ## Affected packages - `mcp-atlassian` (PyPI): affected `<0.22.0`; fixed in `0.22.0` ## Machine-written summary Summary written by Claude Haiku from the source advisory. Not reviewed by a person. > The mcp-atlassian PyPI package, versions before 0.22.0, does not fully enforce the JIRA_PROJECTS_FILTER and CONFLUENCE_SPACES_FILTER restrictions. An attacker who can send queries to the MCP server, such as a prompt-injected LLM agent, can read content from Jira or Confluence projects and spaces outside the operator's allowlist. Upgrade to mcp-atlassian 0.22.0 or later. The source gives few details on any workaround other than restricting untrusted MCP client input. Written 1 Nov 2026. ## Not analysed yet We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check. ## Severity and exploitation - 8.3 High, CVSS 4.0: `CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/SC:H/SI:N/SA:N`, from CNA (GitHub_M) - **CISA KEV:** Not listed. - **EPSS:** 0.0027, the 18th percentile, on 5 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days. ## Timeline - 31 Oct 2026, 14:09 UTC: First seen by agentprime - 31 Oct 2026, 14:09 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-w66g-j6c4-hcfc) ## Sources - [GitHub Advisory Database: GHSA-w66g-j6c4-hcfc](https://github.com/advisories/GHSA-w66g-j6c4-hcfc) - [OSV: GHSA-w66g-j6c4-hcfc](https://osv.dev/vulnerability/GHSA-w66g-j6c4-hcfc) - - - - - - Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code. ## Check whether this affects you A Match means an installed version is in the affected range above. Most don’t affect the app; agentprime hasn’t analysed this one yet. - With the agentprime MCP server (), ask your agent to check the project: `check_lockfile` sends a lockfile, `check_packages` a list of installed packages, and both return the Matches and the upgrades that clear them. `get_advisory` returns this record. Setup: - In a browser: reads your lockfile in the browser, never uploading it. - Whether it touches your code, with file and line: the Claude Code plugin, - As JSON: , or `POST https://api.agentprime.io/v1/match` with your packages () --- The web page: . Everything for agents: .