k8s
Operate the joelclaw Kubernetes cluster — Talos Linux on Colima (Mac Mini). Deploy services, check health, debug pods, recover from restarts, add ports, manage Helm releases, inspect logs, fix networking. Triggers on: 'kubectl', 'pods', 'deploy to k8s', 'cluster health', 'restart pod', 'helm install', 'talosctl', 'colima', 'nodeport', 'flannel', 'port mapping', 'k8s down', 'cluster not working', 'add a port', 'PVC', 'storage', any k8s/Talos/Colima infrastructure task. Also triggers on service-specific deploy: 'deploy redis', 'redeploy inngest', 'livekit helm', 'pds not responding'.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Security
3 findings — 3 medium severity. This skill can be installed but you should review these findings before use.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 0.90). The Agent Runner section in SKILL.md explicitly requires materializing a repository from a supplied REPO_URL/REPO_BRANCH and then executing the fetched AGENT_PROGRAM (and the docs also show fetching remote Helm/chart URLs like raw GitHub and external helm repos), which means the skill will fetch and run arbitrary third‑party/user repository content that can influence agent actions.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 0.90). The skill's agent-runner explicitly materializes and executes code from a remote git repository at runtime via the REPO_URL/REPO_BRANCH/BASE_SHA workflow (i.e., fetching arbitrary repo content to run AGENT_PROGRAM), and the docs also instruct runtime commands that fetch and apply remote manifests such as https://raw.githubusercontent.com/rancher/local-path-provisioner/v0.0.30/deploy/local-path-storage.yaml — both are runtime fetches that execute external code and thus present a high-risk external dependency.
W013: Attempt to modify system services in skill instructions
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
Attempt to modify system services in skill instructions detected (high risk: 0.90). The skill contains explicit host-level, state-changing operations that require elevated privileges—e.g., running `sudo modprobe` on the Colima VM, editing Docker/Colima hostconfig and launchd plists, recreating containers and port mappings—so it encourages the agent to modify the machine state and use sudo.
- Repository
- joelhooks/joelclaw
- Commit
825972c
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.