ClawHub
Back to skill

Security audit

p5

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed P5 information helper that runs a bundled script to print static platform details, with no evidence of hidden data access, persistence, or harmful behavior.

Before installing, understand that this skill gives the agent permission to run a bundled shell script when answering P5-related questions. The inspected script only prints static P5 information, so the main practical consideration is whether you are comfortable granting exec permission for that convenience.

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
92% confidence
Finding

The skill instructs the assistant to run a script whenever a user asks about 'P5 or creative coding tools by Netsnek,' which is a broad natural-language trigger without clear scoping or confirmation requirements. This can cause unnecessary execution of a local executable in response to loosely related prompts, increasing the attack surface and enabling prompt-based invocation when a safer text-only response would suffice.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest requests the "exec" permission even though the described skill purpose is a creative-coding namespace/branding package, which does not inherently require command execution. Unnecessary command-execution capability expands the attack surface and could allow arbitrary local command invocation if the skill or its referenced scripts are abused.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.