Skills/Docker MCP Catalog/aks

aks@r2

CAUTION

Publisher claims: "Azure Kubernetes Service (AKS) official MCP server" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry Docker MCP CatalogPublisher azure · joined 2 days agoInstalls 19,254Last detonated 2 h ago
What would fix thisWatchDispute verdict

Is aks@r2 safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-27 and scored it 65/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive file system command detected; Destructive file system command detected; Authorization escalation language. 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

HIGH
Destructive file system command detectedinternal/security/validator_test.go:594 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedinternal/security/validator_test.go:873 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Authorization escalation languageprompts/azure-fleet-tools.md:280 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Authorization escalation languageprompts/README.md:41 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsinternal/azcli/login_test.go:241 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Authorization escalation languageprompts/azure-cli-tools.md:65 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsinternal/azcli/login_test.go:403 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Destructive command against a filesystem root or deviceinternal/security/validator_test.go:873 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Authorization escalation languageprompts/azure-fleet-tools.md:108 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsinternal/security/validator_test.go:728 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Authorization escalation languageCONTRIBUTING.md:271 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Authorization escalation languageprompts/azure-fleet-tools.md:286 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Destructive command against a filesystem root or deviceinternal/security/validator_test.go:814 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsinternal/security/validator_test.go:642 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsinternal/security/validator_test.go:636 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsinternal/security/validator_test.go:853 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Destructive command against a filesystem root or deviceinternal/security/validator_test.go:967 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Hidden zero-width characters detectedprompts/azure-resource-health.md:2 · Hidden zero-width characters detected — may conceal contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
HIGH
Destructive file system command detectedinternal/security/validator_test.go:967 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Authorization escalation languageprompts/azure-monitor-tools.md:95 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Authorization escalation languageprompts/azure-fleet-tools.md:82 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Authorization escalation languageprompts/azure-cli-tools.md:36 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Destructive file system command detectedinternal/security/validator_test.go:878 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsinternal/azcli/login_test.go:408 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Authorization escalation languageprompts/azure-cli-tools.md:28 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Destructive command against a filesystem root or deviceinternal/security/validator_test.go:878 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Authorization escalation languageprompts/azure-fleet-tools.md:181 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Destructive file system command detectedinternal/security/validator_test.go:814 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Destructive command against a filesystem root or deviceinternal/security/validator_test.go:594 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsinternal/security/validator_test.go:729 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

What would make this Verified

15 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Destructive command against a filesystem root or device≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  2. Unclaimed publisher≈ +8 on the totalClaim azure: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  6. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
Publish a new version to Docker MCP Catalog, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim azure