ClawHub
Back to skill

Security audit

solution-research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed deep-research workflow for comparing technical solutions, with no hidden code, persistence, or destructive behavior found.

Install this if you want an agent to do exhaustive, evidence-heavy technical solution research. Be aware that it may spend significant time and tool usage on web searches, GitHub issue review, source inspection, and video analysis; for quick brainstorming or non-English ecosystems, explicitly constrain the agent's scope and preferred language.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
92% confidence
Finding

The skill description is broad enough to trigger on many ordinary requests about choosing tools, products, or approaches, which can cause the agent to invoke an aggressive external-research workflow when the user did not ask for it. In this skill, that matters more because the workflow mandates exhaustive searching and data collection, increasing the chance of unnecessary web access, over-collection, and misaligned behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Mandating English-only research removes user choice and can bias the evidence base toward English-language sources, potentially excluding more relevant or authoritative material in the user's language or the ecosystem's primary language. In this skill, the requirement is strict and paired with a 'must follow this workflow' tone, making the behavior more rigid and more likely to ignore user preferences or context.

Content

No source excerpt is available for this finding.