ClawHub
Back to skill

Security audit

Principle Synthesizer

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill gives a structured method for synthesizing principles from user-provided sources, with one documentation inconsistency about possible review-file persistence.

Before installing, note that the skill may process the source text you provide through your configured LLM service. The publisher should clarify whether drifted items are ever written to requires_review.md; until then, treat that reference as a possible review artifact and avoid feeding highly sensitive source text unless your agent environment is approved for it.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill explicitly states it does not write files to disk, yet later documentation says drifted items are added to requires_review.md. That contradiction can mislead users and hosting agents about side effects, weakening trust-boundary assumptions and potentially causing unintended data persistence of sensitive source content.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.