{"items":[{"id":"NVI-00016378","kind":"vulnerability","title":"MCP Atlassian: JIRA_PROJECTS_FILTER / CONFLUENCE_SPACES_FILTER allow forbidden-project content exfiltration (one LIVE-proven on Atlassian Cloud)","revision":1,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected."],"lifecycle":"active","identifiers":["GHSA-w66g-j6c4-hcfc","CVE-2026-77251"],"plain_summary":"GitHub lists this reviewed advisory for mcp-atlassian. Published version ranges and source prerequisites are shown below; this is not an inspection of a visitor’s application.","review_status":"source_listed","control_topics":[],"public_actions":[{"summary":"Identify the exact component and deployed version, examine the linked publisher’s conditions, and retain evidence of any mitigation.","source_ids":["sr-6c69009bbaa8a2291a7e5807821efd61"],"action_type":"investigate","limitations":"Confirm current vendor support, compatibility and deployment evidence. This report has not tested a fix in your system.","current_supported_target":null}],"schema_version":"1.1.0","source_metrics":[],"why_it_matters":"Published affected context helps an owner decide what evidence to gather. This report has not examined your application.","related_sources":[{"id":"sr-6c69009bbaa8a2291a7e5807821efd61","url":"https://github.com/advisories/GHSA-w66g-j6c4-hcfc","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-w66g-j6c4-hcfc","publisher":"GitHub Advisory Database","observed_at":"2026-11-01T14:29:31.527Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-6c69009bbaa8a2291a7e5807821efd61"],"technology":"mcp-atlassian","known_exclusions":[],"conditions_summary":"### Summary\n\n`mcp-atlassian` is a popular community MCP server wrapper exposing Jira / Confluence to MCP clients. Operators commonly restrict the surface to a small allowlist of projects/spaces via the `JIRA_PROJECTS_FILTER` and `CONFLUENCE_SPACES_FILTER` environment variables, which the README documents as the principal mechanism for limiting attacker-controlled MCP clients (= prompt-injected LLM agents) to the operator's intended subset of the workspace.\n\nWe identified **three distinct sub-bugs** that let attacker-controlled queries read content from **forbidden** projects/spaces (= projects NOT in the operator's filter) despite the filter being correctly set. The most severe is **empirically reproduced on production Atlassian Cloud** with real operator credentials and sentinel content in two real projects.\n\n| Sub-bug | Layer | Class | Live? |\n|---|---|---|---|\n| **A1** | Jira `jira_search` `jql` | substring-bypass | 🔴 **LIVE PROVEN 2026-05-18 on real Atlassian Cloud** |\n| **A2** | Confluence `confluence_search` `cql` | case-sensitive substring-bypass | code-level verified |\n| **B** | Jira agile `get_board_issues` / `get_agile_boards` | zero-filter (missing check) | code-level v","public_affected_ranges":["< 0.22.0"]}],"null_published_at":"2026-11-04T10:04:27.937Z","source_updated_at":"2026-09-22T20:34:50.000Z","source_disclosed_at":"2026-09-22T20:34:47.000Z","is_synthetic_fixture":false,"null_last_reviewed_at":null,"public_change_summary":"First indexed by Null; source disclosure date is shown separately.","null_first_observed_at":"2026-11-01T14:29:31.527Z"}],"next_cursor":null,"snapshot_revision":"42594"}