ClawHub
Back to skill

Security audit

regression-hunt

Security checks for vulnerabilities and agentic risk

Overview

This skill is a purpose-aligned regression-analysis guide with no bundled executable code, persistence, credential access, or hidden network behavior.

Install this if you want agents to perform deeper regression checks that may read broadly across a repository and run tests. Be aware its natural-language triggers are fairly broad, so use explicit wording when you do or do not want a regression hunt.

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
94% confidence
Finding

The skill advertises activation on broad natural-language phrases like 'what could this break', 'impact of this change', and 'what else uses this', which are common in normal development conversation and not uniquely tied to invoking this skill. In agentic systems that auto-route based on phrase matching, this can cause unintended invocation, leading to unnecessary repository analysis, extra tool use, and execution of costly test workflows without clear user intent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The usage section repeats the same ambiguous trigger phrases and reinforces auto-trigger behavior without sufficiently constraining activation to cases where a concrete code change is in scope. This increases the chance that orchestration logic will over-match routine requests and dispatch the skill inappropriately, amplifying unnecessary analysis and test execution across repositories.

Content

No source excerpt is available for this finding.