ClawHub
Back to skill

Security audit

claw-superpowers

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed software-development workflow guide with approval gates for risky actions and no executable payloads.

Install this if you want your agent to follow a stricter software-development process. Expect it to encourage tests, reviews, worktrees, branches, and subagents for larger tasks; review commands before approving repository-controlled execution or git changes.

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)

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · SKILL.md (reported line 976)May include surrounding context.

md
### Skill Creation Checklist

**RED:** Create pressure scenarios → run WITHOUT skill → document baseline failures (exact rationalizations agents use)
**GREEN:** Write skill addressing specific failures → run WITH skill → verify compliance
**REFACTOR:** Find new rationalizations → add counters → re-test until bulletproof

### Common Rationalizations for Skipping Testing

Autonomous Decision Making

Medium
Category
Excessive Agency
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.

Content

Scanner excerpt · SKILL.md (reported line 245)May include surrounding context.

md
### Rules

- Follow plan steps exactly
- Don't skip verifications
- Between batches: report and wait
- Stop when blocked, don't guess
- Never start implementation on main/master without explicit consent

Autonomous Decision Making

Medium
Category
Excessive Agency
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.

Content

Scanner excerpt · SKILL.md (reported line 305)May include surrounding context.

md
### Rules

- Never start on main/master without consent
- Never skip reviews (spec OR quality)
- Spec review BEFORE code quality review
- Don't dispatch parallel implementation subagents (conflicts)

Static analysis

No suspicious patterns detected.