ClawHub
Back to skill

Security audit

Validation Rules Builder

Security checks for vulnerabilities and agentic risk

Overview

This is a local construction-data validation helper with some scope and correctness caveats, but no evidence of hidden access, persistence, exfiltration, or destructive behavior.

Before installing, treat this as a construction data validation aid, not a fully verified estimating engine. Review outputs carefully, especially schedule date checks and any cost-estimate results, and only provide files you intend the agent to read or export.

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 (3)

Intent-Code Divergence

Medium
Confidence
96% confidence
Finding
The schedule validator defines a dates_valid function suggesting start/end date consistency should be enforced, but that logic is never registered as a rule and therefore never executes. This can let invalid schedules with end dates before start dates pass validation, undermining downstream planning, reporting, or automation that assumes validated schedule data is trustworthy.

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The instructional content conflicts with the stated purpose of building validation rules by directing the assistant to gather inputs and process cost estimates using external skill methods. Conflicting intent is dangerous because it creates ambiguous behavior, making the agent more likely to follow the wrong workflow and expose capabilities beyond what users and reviewers expect.

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The instructions introduce cost-estimation and cost-analysis workflows even though the skill metadata describes a validation-rules builder for construction data. This scope expansion can cause the agent to perform unintended financial-analysis tasks, increasing the chance of misuse, incorrect outputs, or policy bypass through undocumented functionality referenced from SKILL.md.

Static analysis

No suspicious patterns detected.