ClawHub
Back to skill

Security audit

writing-plans

Security checks for vulnerabilities and agentic risk

Overview

This skill is a planning aid that writes implementation plans and does not show hidden, destructive, credential-seeking, or exfiltration behavior.

Before installing, be aware that this skill may activate for broad multi-step coding requests and may create plan files under docs/superpowers/plans by default. Review generated plans before choosing any execution handoff, especially if they include commits or subagent-driven work.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description says to use this skill whenever there is 'a spec or requirements for a multi-step task, before touching code,' which is a wide and somewhat ambiguous trigger for many normal software conversations. It does not provide explicit exclusion conditions or concrete negative examples to clarify when ordinary discussion should not invoke the skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.