cockroachdb@0.1.10

CAUTION

Publisher claims: "Connect Claude Code directly to your CockroachDB clusters for hands-on database work — explore schemas, write optimized SQL, debug queries, and manage distributed database clusters. This plugin provides 14 tools across two active MCP backends (self-hosted MCP Toolbox and managed CockroachDB Cloud MCP Server), three specialized agents (DBA, Developer, Operator), 32 skills across 6 operational domains, and built-in safety hooks." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry Claude Code plugin marketplacePublisher cockroachdb · joined 0 days agoInstalls 0Last detonated 2 h ago

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-26 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: False input termination marker; Authorization escalation language; Outbound HTTP to raw IP address. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only

Static findings

CRITICAL
False input termination markerskills/cockroachdb-security-and-governance/configuring-sso-and-scim/SKILL.md:278 · False input termination marker — attempts to end user input sectionFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Authorization escalation languageskills/cockroachdb-observability-and-diagnostics/analyzing-range-distribution/references/permissions.md:174 · Authorization escalation languageFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST01
HIGH
Outbound HTTP to raw IP address.mcp.json:17 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Privileged sudo commandskills/cockroachdb-operations-and-lifecycle/performing-cluster-maintenance/SKILL.md:142 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Authorization escalation languageskills/cockroachdb-security-and-governance/auditing-cis-benchmark/references/cis-controls.md:378 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Authorization escalation languageskills/cockroachdb-operations-and-lifecycle/managing-certificates-and-encryption/SKILL.md:4 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Privileged sudo commandskills/cockroachdb-operations-and-lifecycle/performing-cluster-maintenance/SKILL.md:140 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Authorization escalation languageskills/cockroachdb-security-and-governance/auditing-cis-benchmark/references/cis-controls.md:362 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Authorization escalation languageskills/cockroachdb-security-and-governance/auditing-cloud-cluster-security/SKILL.md:507 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Privileged sudo commandskills/cockroachdb-operations-and-lifecycle/upgrading-cluster-version/SKILL.md:115 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
False input termination markerskills/cockroachdb-security-and-governance/configuring-sso-and-scim/references/configuration-steps.md:290 · False input termination marker — attempts to end user input sectionFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Privileged sudo commandskills/cockroachdb-operations-and-lifecycle/upgrading-cluster-version/SKILL.md:118 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Authorization escalation languageskills/cockroachdb-security-and-governance/auditing-cis-benchmark/SKILL.md:115 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Privileged sudo commandskills/cockroachdb-security-and-governance/auditing-cis-benchmark/SKILL.md:115 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandskills/cockroachdb-application-development/designing-multi-region-applications/SKILL.md:315 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandskills/cockroachdb-operations-and-lifecycle/performing-cluster-maintenance/SKILL.md:152 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandskills/cockroachdb-onboarding-and-migrations/setting-up-local-cluster/SKILL.md:137 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandskills/cockroachdb-operations-and-lifecycle/managing-certificates-and-encryption/SKILL.md:97 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandscripts/setup-cockroachdb.sh:334 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/setup-cockroachdb.sh:336 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandscripts/setup-cockroachdb.sh:135 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Authorization escalation languageskills/cockroachdb-security-and-governance/managing-tls-certificates/SKILL.md:4 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandscripts/setup-cockroachdb.sh:340 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandskills/cockroachdb-operations-and-lifecycle/performing-cluster-maintenance/SKILL.md:147 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Authorization escalation languageskills/cockroachdb-security-and-governance/hardening-user-privileges/SKILL.md:64 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandscripts/setup-cockroachdb.sh:332 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Authorization escalation languageskills/cockroachdb-security-and-governance/configuring-sso-and-scim/SKILL.md:463 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandskills/cockroachdb-onboarding-and-migrations/setting-up-local-cluster/SKILL.md:135 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
URL using raw IP address.mcp.json:17 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Process kill commandskills/cockroachdb-operations-and-lifecycle/managing-certificates-and-encryption/SKILL.md:151 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionscripts/test-hooks.sh:58 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandskills/cockroachdb-onboarding-and-migrations/setting-up-local-cluster/SKILL.md:136 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Authorization escalation languageskills/cockroachdb-security-and-governance/managing-tls-certificates/SKILL.md:32 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandscripts/setup-cockroachdb.sh:158 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Authorization escalation languageskills/cockroachdb-security-and-governance/hardening-user-privileges/SKILL.md:3 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandskills/cockroachdb-security-and-governance/managing-tls-certificates/SKILL.md:195 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandskills/cockroachdb-security-and-governance/managing-tls-certificates/SKILL.md:282 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim cockroachdb: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Outbound HTTP to raw IP address≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  3. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  6. URL using raw IP address≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
Publish a new version to Claude Code plugins, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim cockroachdb