ClawHub
Back to skill

Security audit

Agent Prompt Patterns

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill that teaches agent safety and reliability patterns, with sensitive examples framed as requiring approval or safeguards.

Install this as a reference guide, not as an automatic policy engine. If you copy its templates into an agent, review the approval tiers carefully and keep email sending, deletion outside the workspace, financial transactions, access-control changes, and public posting under explicit human control.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
```markdown
## Advisory Mode Configuration (AGENTS.md)

### Tier: Low (auto-approve after 3-day probation)
- Read any file in workspace
- Search codebase
- Generate summaries to memory files
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.

Session Persistence

Medium
Category
Rogue Agent
Content
### Tier: High (2-week probation, never fully autonomous)
- Git commit and push
- Create pull requests
- Post to Slack channels
- Modify cron jobs
Confidence
60% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
```
Level 1: Prose Rule (in AGENTS.md)
  "Don't send emails without approval"
  → Relies on agent reading and following the rule
  → Appropriate for: new rules, low-risk guidelines
Confidence
75% 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.