
Loading

Loading
We use strictly necessary cookies to run this site, and analytics cookies to understand how it's used. See our Privacy Policy for details.
A GitHub-reviewed security advisory, not necessarily under active exploitation the way our CISA KEV advisories are, but a real, disclosed vulnerability in an open-source dependency.
Affected packages
Vulnerable: < 2.0.8
Patched in 2.0.8
Details
The domshell_eval MCP tool (and the eval command inside domshell_execute) was classified as read-tier, allowing it to run without the --allow-write server flag. However, eval and the write-tier js command dispatch to the same handler in the extension and call CDP Runtime.evaluate with the raw expression string and no side-effect gate. Any JavaScript expression could therefore mutate DOM, window, or global state through domshell_eval without the operator's --allow-write authorization.
The tool description explicitly promised "(read-only) ... always available in read-only mode" — the misclassification contradicted the documented contract, not just an implicit one.
No new capability was exposed — the same write access was already available via domshell_js with --allow-write — but the tier misclassification meant:
readOnlyHint: true)--allow-write) misrepresented what an AI agent was actually authorized to doeval callFraming: OWASP LLM Top 10 LLM06 (Excessive Agency), NIST AI RMF (tool permission boundary + human-approval fidelity), CWE-863 (Incorrect Authorization).
The reporter's main framing: the MCP approval UI and server-side permission model can misrepresent the actual agency being granted to an AI agent.
mcp-server/index.ts:113 — WRITE_COMMANDS excluded evalmcp-server/index.ts:879-887 — domshell_eval registered with ANNO_READ and description asserting read-onlysrc/background/index.ts:1849-1854 — js and eval both dispatch to handleJs(rawCode)src/background/index.ts:3282 — handleJs calls cdp.evaluateJs(code)src/background/cdp_client.ts:660-667 — evaluateJs sends Runtime.evaluate with expression: code, returnByValue: true, awaitPromise: true and no throwOnSideEffect gateShipped in @apireno/[email protected] (2026-07-08):
eval added to WRITE_COMMANDS, aligning tier with actual capabilitydomshell_eval MCP annotation changed from ANNO_READ to ANNO_WRITEMCP_INSTRUCTIONS updated to remove read-only language; read-only DOM inspection needs pointed at domshell_cat / domshell_text / domshell_findSECURITY.md added + GitHub Private Vulnerability Reporting enabled on the reponpm install @apireno/[email protected]
Or, in a persistent install, restart your MCP server against the new version.
Drives that call eval without --allow-write will start receiving Error: 'eval' requires --allow-write. Options:
--allow-write to the server flags if eval's write capability is actually neededdomshell_cat / domshell_text / domshell_finddomshell_js if the caller already runs with --allow-write (same tier, same capability)eval or js commands (verified by grep).--allow-write for their action gates.domshell_eval without --allow-write will now be denied, aligning behavior with the documented contract.Ugur Ozer, AI Risk Management https://airiskmanagement.ca [email protected]
Source-review-first responsible disclosure via private email to the maintainer on 2026-07-08. Reporter finding id: DOMSHELL-EVAL-READ-TIER-BYPASS-001. Ugur followed the standard disclosure ladder correctly despite the missing SECURITY.md at time of report — that gap has now been closed (repo now has SECURITY.md + GitHub Private Vulnerability Reporting enabled).
main at 2d63dab; fix planned@apireno/[email protected] released to npm and the MCP registry; SECURITY.md added; GitHub PVR enabledEPSS, exploit probability
Low0.11%
estimated chance of real-world exploitation in the next 30 days, higher than 1.3% of every CVE FIRST.org scores
Refreshed 11/19/2026, via FIRST.org's EPSS model, not CVSS, this measures likelihood of exploitation, not how severe it would be.
More npm advisories
Talk to us about this
Find out whether this dependency (or others like it) is actually reachable in your codebase.
Get help patching, or building dependency-scanning into your pipeline going forward.
A secure code review or supply chain review finds this before an advisory does.