scopeblind-gateway

⚠️ This repository has moved. Active development continues at ScopeBlind/scopeblind-gateway. This personal fork may be behind the canonical repository. Please use the org repo for issues, pull requests, and the latest code. protect-mcp Security gateway for MCP servers. Shadow-mode logs by default,...

CVE-2026-100537

OpenClaw npm package 'openclaw' before 2026.8.1 fails to apply the originating requester's effective tool policy during Active Memory automatic recall. In deployments that use Active Memory together with requester-specific tool rules, deterministic and hidden recall paths can retrieve durable...

CVE-2026-100552

OpenClaw npm package 'openclaw' before 2026.8.1 does not correctly enforce per-chat tool policies for Codex app-server runtime tools. A conversation-level tools.allow rule filtered OpenClaw tools but did not restrict the shell, process, file, and patch tools owned by the Codex runtime. When a...

EUVD-2026-87498

OpenClaw npm package 'openclaw' before 2026.8.1 does not correctly enforce per-chat tool policies for Codex app-server runtime tools. A conversation-level tools.allow rule filtered OpenClaw tools but did not restrict the shell, process, file, and patch tools owned by the Codex runtime. When a...

CVE-2026-100537 OpenClaw before 2026.8.1 Authentication Bypass via Active Memory

OpenClaw npm package 'openclaw' before 2026.8.1 fails to apply the originating requester's effective tool policy during Active Memory automatic recall. In deployments that use Active Memory together with requester-specific tool rules, deterministic and hidden recall paths can retrieve durable...

CVE-2026-100537 OpenClaw before 2026.8.1 Authentication Bypass via Active Memory

OpenClaw npm package 'openclaw' before 2026.8.1 fails to apply the originating requester's effective tool policy during Active Memory automatic recall. In deployments that use Active Memory together with requester-specific tool rules, deterministic and hidden recall paths can retrieve durable...

CVE-2026-100537

The OpenClaw (npm package 'openclaw' ) before version 2026.8.1 contains a vulnerability where it fails to apply a requester's effective tool policy during Active Memory automatic recall . In environments using Active Memory with requester-specific rules, hidden recall paths can retrieve durable m...

EUVD-2026-87513

OpenClaw npm package 'openclaw' before 2026.8.1 fails to apply the originating requester's effective tool policy during Active Memory automatic recall. In deployments that use Active Memory together with requester-specific tool rules, deterministic and hidden recall paths can retrieve durable...

CVE-2026-100537

OpenClaw npm package 'openclaw' before 2026.8.1 fails to apply the originating requester's effective tool policy during Active Memory automatic recall. In deployments that use Active Memory together with requester-specific tool rules, deterministic and hidden recall paths can retrieve durable...

PT-2026-99174

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.8.1 Description The software fails to apply the originating requester's effective tool policy during Active Memory automatic recall. In deployments using Active Memory with requester-specific tool rules,...

PT-2026-99189

Name of the Vulnerable Software and Affected Versions openclaw versions prior to 2026.8.1 Description The software fails to correctly enforce per-chat tool policies for Codex app-server runtime tools. Specifically, a conversation-level tools.allow rule filters OpenClaw tools but fails to restrict...

PYSEC-2026-3520 PraisonAI recipe.run_stream skips dangerous-tool policy enforcement

PraisonAI recipe.runstream skips dangerous-tool policy enforcement Summary PraisonAI recipe execution blocks default-denied dangerous tools unless the caller explicitly passes allowdangeroustools=True. The normal recipe.run path enforces this with checktoolpolicy. The streaming path,...

PraisonAI recipe.run_stream skips dangerous-tool policy enforcement

PraisonAI recipe.runstream skips dangerous-tool policy enforcement SummaryPraisonAI recipe execution blocks default-denied dangerous tools unless thecaller explicitly passes allowdangeroustools=True. The normal recipe.runpath enforces this with checktoolpolicy. The streaming path,recipe.runstream...

PT-2026-64112

Summary PraisonAI recipe execution has a dangerous-tool policy that is supposed to block default-denied tools unless the caller explicitly passes allow dangerous tools=True. That policy only checks tools declared in TEMPLATE.yaml requires.tools. For steps-based recipes, the actual execution path...

PT-2026-64123

PraisonAI recipe.run stream skips dangerous-tool policy enforcement Summary PraisonAI recipe execution blocks default-denied dangerous tools unless the caller explicitly passes allow dangerous tools=True. The normal recipe.run path enforces this with check tool policy. The streaming path,...

CVE-2026-62225

OpenClaw versions before 2026.5.18 contain an authorization bypass vulnerability in skill command dispatch that allows lower-trust callers to execute or persist actions beyond their intended authorization. Attackers can bypass tool policy restrictions through configured input paths to perform...

CVE-2026-62225: Incorrect Authorization

OpenClaw versions before 2026.5.18 contain an authorization bypass vulnerability in skill command dispatch that allows lower-trust callers to execute or persist actions beyond their intended authorization. Attackers can bypass tool policy restrictions through configured input paths to perform...

GHSA-V847-HXXW-3PXG PraisonAI recipe.run_stream skips dangerous-tool policy enforcement

PraisonAI recipe.runstream skips dangerous-tool policy enforcement Summary PraisonAI recipe execution blocks default-denied dangerous tools unless the caller explicitly passes allowdangeroustools=True. The normal recipe.run path enforces this with checktoolpolicy. The streaming path,...

GHSA-985F-72MJ-8GF7 OpenClaw: Tool group policy callers could accept unvalidated group IDs

Summary Tool group policy callers could accept unvalidated group IDs. In affected versions, a caller that can supply a group id to the affected policy resolver could resolve policy for an unvalidated group id. This advisory is scoped to the named feature and configuration. It does not change...

OpenClaw: Tool group policy callers could accept unvalidated group IDs

Summary Tool group policy callers could accept unvalidated group IDs. In affected versions, a caller that can supply a group id to the affected policy resolver could resolve policy for an unvalidated group id. This advisory is scoped to the named feature and configuration. It does not change...