AAK-MCP-AGENTICMAIL-CVE-2026-57495-001: AgenticMail bridge-wake indirect prompt injection (unpinned @agenticmail/* below fix)
- Severity
- HIGH
- Category
- Supply Chain (
supply-chain) - Scanner
agent_audit_kit/scanners/mcp_cve_pins_2026_07.py- Auto-fixable
- No.
- SARIF name
AgenticMailBridgeWakeInjection
What it detects
AgenticMail gives AI agents real email addresses. In @agenticmail/claudecode < 0.2.39, @agenticmail/codex < 0.1.33, @agenticmail/core < 0.9.43, and @agenticmail/openclaw < 0.5.71, two inbound-mail handlers act on a privileged effect without verifying the sender is the operator (a sibling handler gates the same untrusted From provenance fail-closed with isOperatorReplySender). The high-impact path: any external email routed to the bridge inbox resumes the operator's Claude Code session with permissionMode: 'bypassPermissions', embedding the attacker-controlled from/subject/preview verbatim into the prompt — an indirect prompt injection into a fully-privileged agent (Bash/Write/Edit/WebFetch + the agenticmail MCP toolbelt) running as the operator's OAuth identity (CVE-2026-57495). Fixed in @agenticmail/claudecode 0.2.39, @agenticmail/codex 0.1.33, @agenticmail/core 0.9.43, and @agenticmail/openclaw 0.5.71.
How to fix
Upgrade every @agenticmail/* package to the fixed release and pin it (@agenticmail/claudecode >= 0.2.39, @agenticmail/codex >= 0.1.33, @agenticmail/core >= 0.9.43, @agenticmail/openclaw >= 0.5.71). Gate every privileged inbound-mail effect on operator-sender provenance (fail closed), and never resume a bypassPermissions agent from untrusted From mail.
To confirm the finding is gone, report only this rule:
agent-audit-kit scan . --rules AAK-MCP-AGENTICMAIL-CVE-2026-57495-001
Limitations
Reads @agenticmail/claudecode, @agenticmail/codex, @agenticmail/core and @agenticmail/openclaw, each against its own fix floor, in requirements*.txt at any depth and, at the project root only, in pyproject.toml, Pipfile, package.json, .mcp.json, mcp.json, claude_desktop_config.json and the Pipfile.lock, poetry.lock, uv.lock, package-lock.json, pnpm-lock.yaml and yarn.lock lockfiles, taking the lowest version a range allows and reporting a reference that states no version. The dependency is not read when it is declared in a sub-directory manifest (packages/app/package.json) or in a lockfile format the reader does not parse (a Yarn 2+ yarn.lock). A file over 2 MB, or a lockfile over 32 MiB, is not read. A declaration nested more than 64 levels deep in package.json, a TOML manifest or an MCP config (an MCP server more than 62) is still judged, and reported without a line; a lockfile entry keeps its line at any depth.
References
- CVE: CVE-2026-57495
- OWASP MCP Top 10: MCP04:2025 (Software Supply Chain Attacks & Dependency Tampering), MCP06:2025 (Intent Flow Subversion)
- OWASP Agentic Top 10: ASI01 (Agent Goal Hijack), ASI04 (Agentic Supply Chain Vulnerabilities)
- Adversa AI MCP Top 25 (AAK-defined ids): ADV-AUTH-01 (Missing Authentication)
- CSA AI Controls Matrix (AICM): AIS-07, AIS-12, STA-08
All rules. This page is generated from the rule registry when the documentation is built; to change it, change the rule in agent_audit_kit/rules/builtin.py. To give the rule a hand-written write-up, add docs/rules/AAK-MCP-AGENTICMAIL-CVE-2026-57495-001.md: the page then shows that text, with the registry reference appended under it.