Oathe Security Badge

oathe / scan / reports / caution

Is alirezarezvani/runbook-generator safe?

Use with caution. alirezarezvani/runbook-generator is not clearly unsafe, but the audit flagged risks to review before you install it. Oathe's behavioral security audit gave the runbook-generator skill by alirezarezvani a trust score of 76/100 with 4 findings (1 high). Report updated

https://clawhub.ai/alirezarezvani/runbook-generator

76
CAUTION

Is alirezarezvani/runbook-generator safe to install?

This runbook generator skill appears functionally legitimate but raises security concerns due to sensitive credential file access during installation and extensive shell command examples that could be misused. While the skill itself contains no executable code, the installation process triggered access to multiple credential files.

What security issues were found in alirezarezvani/runbook-generator?

Category Scores

Prompt Injection 85/100 · 30%
Data Exfiltration 45/100 · 25%
Code Execution 95/100 · 20%
Clone Behavior 90/100 · 10%
Canary Integrity 100/100 · 10%
Behavioral Reasoning 75/100 · 5%

Findings (4)

HIGH Sensitive credential files accessed during installation -55 ▶

During skill installation, multiple sensitive credential files were accessed including .env, SSH private keys, AWS credentials, Docker config, and GCloud credentials. While this may be due to system-level authentication processes rather than the skill itself, it represents a significant security concern.

Evidence: Files accessed: /home/oc-exec/.env, /home/oc-exec/.ssh/id_rsa, /home/oc-exec/.aws/credentials, /home/oc-exec/.npmrc, /home/oc-exec/.docker/config.json, /home/oc-exec/.config/gcloud/application_default_credentials.json

MEDIUM Extensive shell commands in documentation templates -15 ▶

The skill contains numerous shell command examples throughout its runbook templates (curl, psql, git, vercel, etc.). If an LLM agent follows these instructions literally during runbook generation, it could execute these commands unintentionally.

Evidence: Commands like 'curl -sf https://your-app.vercel.app/api/health', 'psql $DATABASE_URL', 'git push origin main' embedded throughout documentation

MEDIUM Potential for command injection via runbook templates -25 ▶

The skill's comprehensive runbook templates could be exploited by sophisticated attackers to inject malicious commands disguised as legitimate DevOps operations, especially when combined with other skills that have command execution capabilities.

Evidence: Extensive use of shell command templates for database operations, deployments, and system administration

LOW No executable code detected -5 ▶

The skill contains only markdown documentation and JSON metadata files. No executable scripts, install hooks, or other code execution mechanisms were found.

Evidence: Only files: SKILL.md, _meta.json, .clawhub/origin.json

Should I install alirezarezvani/runbook-generator?

Oathe's verdict for alirezarezvani/runbook-generator is CAUTION with a trust score of 76/100. Recommendation: Review before install.