ClawHub
Back to skill

Security audit

DR. Planning Artifacts

Security checks for vulnerabilities and agentic risk

Overview

This is a planning-template skill that may write requested planning artifacts, but it does not contain hidden execution, credential access, exfiltration, or destructive behavior.

Install this if you want an agent to help formalize and preserve planning work. Be aware that when you say something is locked, the skill may update the clear target document if the agent has write access, so specify the destination and ask for a preview first if you want tighter 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
  • 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 (2)

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 216)May include surrounding context.

Clear outcome: Daniel can request or receive a structured company snapshot with sources, risks, and next actions. In scope: source discovery, data capture, summarization, evidence links, watchlist integration. Out of scope: automated trading, financial advice, portfolio allocation. Success signal: another agent can create features and stories from this epic without asking what the engine is supposed to do.

text

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly tells the agent to update a durable destination whenever write access exists, without requiring visible user confirmation at the time of modification. In an agent setting, this can lead to silent file or artifact changes that the user did not intend, especially when the destination seems 'clear' only from the agent's perspective.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.