ClawHub
Back to skill

Security audit

abe-deep-research

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only research workflow skill that asks the agent to search, evaluate sources, and document findings without hidden persistence or privileged actions.

Install this if you want a structured research workflow. Expect it to encourage broader web searching and more detailed source documentation than a quick lookup; confirm the desired depth before use to avoid unnecessary research time.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The phrase "Load when planning or executing research" is a very broad activation condition for a markdown skill description. It does not define specific trigger phrases, scope boundaries, or exclusion conditions, so it could overlap with many ordinary planning or research-related conversations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.