ClawHub
Back to skill

Security audit

Executing Plans

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain workflow guide for executing a written implementation plan in small reviewed batches, with no bundled code, persistence, or hidden data access.

Install only if you want an agent workflow for executing plans in batches. Review any plan before using it, especially if it includes destructive commands, deployments, secrets, production data, or other high-impact 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill description is open-ended and does not constrain what kinds of implementation plans may be executed, what repositories or environments are in scope, or what safety checks are required before acting. Because the skill instructs the agent to read a plan and then 'follow plan steps exactly,' a broad invocation scope increases the chance that unsafe, over-privileged, or destructive plans are executed without adequate policy boundaries.

Content

No source excerpt is available for this finding.

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 73)May include surrounding context.

md
## Remember
- Review plan critically first
- Follow plan steps exactly
- Don't skip verifications
- Reference skills when plan says to
- Between batches: just report and wait
- Stop when blocked, don't guess

Static analysis

No suspicious patterns detected.