ClawHub
Back to skill

Security audit

Phy Lenny Mentor

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed product-advice skill with broad proactive activation, but it does not contain hidden code, persistence, credential handling, or destructive behavior.

Install this if you want product-management advice to appear proactively in relevant conversations. Be aware that it may offer Lenny-style frameworks during general product discussions and may search local transcript or wisdom files if you have them in the project.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is explicitly configured to trigger 'automatically when relevant' in its frontmatter description, which creates a broad activation surface for ordinary product-related conversations. While this does not directly execute code or exfiltrate data, it can cause unsolicited intervention, increased prompt-surface exposure, and accidental steering of conversations in contexts where the user did not intend to invoke the skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The proactive triggers cover very common business topics like roadmap, prioritization, messaging, PMF, growth, and execution, making activation likely during normal conversation even when the user did not request this skill. In context, this increases the chance of prompt hijacking of routine discussions and may encourage unnecessary tool-like behavior, especially because the skill also instructs the agent to proactively offer insights.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.