Skills/Claude Code plugins/sagemaker-ai

sagemaker-ai@1.3.0

CAUTION

Publisher claims: "Build, train, and deploy AI models with deep AWS AI/ML expertise brought directly into your coding assistants, covering the surface area of Amazon SageMaker AI." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry Claude Code plugin marketplacePublisher awslabs · joined 1 days agoInstalls 0Last detonated 2 h ago
What would fix thisWatchDispute verdict

Is [email protected] 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: Host or command assembled from base64 fragments; Outbound HTTP to raw IP address; Host or command assembled from base64 fragments. 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
Host or command assembled from base64 fragmentsskills/hyperpod-nccl/scripts/nccl-diagnose.sh:1500 · Host or command assembled from base64 fragmentsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Outbound HTTP to raw IP addressskills/hyperpod-nccl/scripts/nccl-diagnose.sh:1547 · 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
Host or command assembled from base64 fragmentsskills/hyperpod-slurm-debugger/scripts/slurm-diagnose.sh:250 · Host or command assembled from base64 fragmentsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Privileged sudo commandskills/hyperpod-ssm/scripts/ssm-exec.sh:105 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandskills/hyperpod-ssm/SKILL.md:96 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Host or command assembled from base64 fragmentsskills/hyperpod-node-debugger/scripts/triage-cluster.sh:164 · Host or command assembled from base64 fragmentsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
File permission modification commandskills/hyperpod-cluster-debugger/scripts/diagnose-cluster.sh:142 · 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
URL using raw IP addressskills/hyperpod-nccl/scripts/nccl-diagnose.sh:1553 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Host or command assembled from base64 fragmentsskills/hyperpod-cluster-debugger/scripts/diagnose-cluster.sh:146 · Host or command assembled from base64 fragmentsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
URL using raw IP addressskills/hyperpod-nccl/scripts/nccl-diagnose.sh:1547 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Outbound HTTP to raw IP addressskills/hyperpod-nccl/scripts/nccl-diagnose.sh:1553 · 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/hyperpod-slurm-debugger/scripts/slurm-diagnose.sh:141 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Host or command assembled from base64 fragmentsskills/hyperpod-node-debugger/scripts/triage-cluster.sh:180 · Host or command assembled from base64 fragmentsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Outbound HTTP to raw IP addressskills/hyperpod-nccl/scripts/nccl-diagnose.sh:1747 · 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
Host or command assembled from base64 fragmentsskills/hyperpod-slurm-debugger/scripts/slurm-diagnose.sh:212 · Host or command assembled from base64 fragmentsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Persistence: instructs the agent to auto-load this skill in future sessionsskills/dataset-transformation/SKILL.md:3 · Persistence: instructs the agent to auto-load this skill in future sessionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Host or command assembled from base64 fragmentsskills/hyperpod-nccl/scripts/nccl-diagnose.sh:1530 · Host or command assembled from base64 fragmentsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Privileged sudo commandskills/hyperpod-ssm/SKILL.md:15 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Outbound HTTP to raw IP addressskills/hyperpod-nccl/scripts/nccl-diagnose.sh:1551 · 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
Outbound HTTP to raw IP addressskills/hyperpod-nccl/scripts/nccl-diagnose.sh:1743 · 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
MEDIUM
URL using raw IP addressskills/hyperpod-nccl/scripts/nccl-diagnose.sh:1551 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Host or command assembled from base64 fragmentsskills/hyperpod-cluster-debugger/scripts/diagnose-cluster.sh:167 · Host or command assembled from base64 fragmentsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
URL using raw IP addressskills/hyperpod-nccl/scripts/nccl-diagnose.sh:1743 · 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
File permission modification commandskills/hyperpod-nccl/scripts/nccl-diagnose.sh:1494 · 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
File permission modification commandskills/hyperpod-ssm/scripts/ssm-exec.sh:41 · 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
URL using raw IP addressskills/hyperpod-nccl/scripts/nccl-diagnose.sh:1747 · 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
File permission modification commandskills/hyperpod-node-debugger/scripts/triage-cluster.sh:158 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

What would make this Verified

15 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim awslabs: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Obfuscated code≈ +5 on the totalRemove base64-assembled strings, eval of decoded text and minified blobs. Reviewers and scanners both treat unreadable code as hostile.
  3. Host or command assembled from base64 fragments≈ +4 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
  4. Outbound HTTP to raw IP address≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  5. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  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 Claude Code plugins, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim awslabs