ClawHub
Back to skill

Security audit

thought-flow

Security checks for vulnerabilities and agentic risk

Overview

This is a workflow guidance skill that shapes planning and debugging behavior, with no executable code or hidden data access.

Install this if you want the agent to follow a structured collaboration loop. Be aware it may activate often because the triggers cover common planning and troubleshooting moments, and review any proposed AGENTS.md or SKILL.md changes before accepting them.

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
92% confidence
Finding

The description says to use the skill when 'starting a new task,' 'proposing a plan,' 'when something fails or looks broken,' and 'when deciding whether to codify knowledge,' which are very broad situations that overlap with common, everyday agent work. It does not provide explicit trigger phrases, exclusion conditions, or narrow scope boundaries, so the activation conditions are ambiguous.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.