ClawHub
Back to skill

Security audit

S³ Incident Runbook Templates

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only incident runbook template skill with expected operational commands, but users should treat those commands as examples requiring approval before use in production.

Install only if you want incident response runbook templates. Before using any generated or copied command in production, confirm the target service, approval path, backups, rollback plan, and incident commander direction, especially for database termination, VACUUM, delete, failover, Kubernetes rollout, scaling, and feature-flag actions.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (10)

External Transmission

Medium
Category
Data Exfiltration
Content
```

### 2. Quick Health Checks
- [ ] Can you reach the service? `curl -I https://api.company.com/payments/health`
- [ ] Database connectivity? Check connection pool metrics
- [ ] External dependencies? Check Stripe, bank API status
- [ ] Recent changes? Check deploy history
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
```

### 2. Quick Health Checks
- [ ] Can you reach the service? `curl -I https://api.company.com/payments/health`
- [ ] Database connectivity? Check connection pool metrics
- [ ] External dependencies? Check Stripe, bank API status
- [ ] Recent changes? Check deploy history
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
```

### 2. Quick Health Checks
- [ ] Can you reach the service? `curl -I https://api.company.com/payments/health`
- [ ] Database connectivity? Check connection pool metrics
- [ ] External dependencies? Check Stripe, bank API status
- [ ] Recent changes? Check deploy history
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
```

### 2. Quick Health Checks
- [ ] Can you reach the service? `curl -I https://api.company.com/payments/health`
- [ ] Database connectivity? Check connection pool metrics
- [ ] External dependencies? Check Stripe, bank API status
- [ ] Recent changes? Check deploy history
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
This runbook includes rollback, scaling, query termination, and configuration-changing commands that can materially affect production systems, but it does not clearly warn operators about prerequisites, approval requirements, blast radius, or recovery risks. In an agent skill context, these steps may be surfaced directly to a user and acted on quickly during an incident, increasing the chance of harmful or premature execution.

External Transmission

Medium
Category
Data Exfiltration
Content
psql -h $DB_HOST -U $DB_USER -c "SELECT pg_terminate_backend(pid);"

# Step 4: Check external dependency latency
curl -w "@curl-format.txt" -o /dev/null -s https://api.stripe.com/v1/health

# Step 5: Enable circuit breaker if dependency is slow
kubectl set env deployment/payment-service \
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
# Go to Sentry: https://sentry.io/payments

# Step 3: If specific endpoint, enable feature flag to disable
curl -X POST https://api.company.com/internal/feature-flags \
  -d '{"flag": "DISABLE_PROBLEMATIC_FEATURE", "enabled": true}'

# Step 4: If data issue, check recent data changes
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
# Go to Sentry: https://sentry.io/payments

# Step 3: If specific endpoint, enable feature flag to disable
curl -X POST https://api.company.com/internal/feature-flags \
  -d '{"flag": "DISABLE_PROBLEMATIC_FEATURE", "enabled": true}'

# Step 4: If data issue, check recent data changes
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The database runbook recommends dangerous actions such as terminating connections, VACUUM FULL, failover consideration, and deleting old data without guardrails about data integrity, lock contention, backup status, replica health, or approval requirements. In a live incident, an operator or agent following these instructions could worsen outages, cause data loss, or create irreversible operational damage.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
### Don'ts
- **Don't assume knowledge** - Write for 3 AM brain
- **Don't skip verification** - Confirm each step worked
- **Don't forget communication** - Keep stakeholders informed
- **Don't work alone** - Escalate early
- **Don't skip postmortems** - Learn from every incident
Confidence
85% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.