ClawHub
Back to skill

Security audit

Scannable Reports

Security checks for vulnerabilities and agentic risk

Overview

This skill only teaches the agent to format chat-friendly reports and does not request access to files, credentials, tools, network, or persistent state.

Install this if you want agents to make progress updates and dashboards easier to read in chat apps. Be aware it may influence formatting for common status-report requests even when you did not explicitly ask for mobile chat formatting.

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
Confidence
92% confidence
Finding
The description says the skill 'Triggers on status reports, dashboards, metrics, progress updates, or when output needs to be mobile-scannable,' which uses broad categories rather than a bounded trigger list. Terms like 'status reports' and 'progress updates' are common everyday requests, and the file provides no exclusion conditions or negative examples to clarify when the skill should not activate.

Static analysis

No suspicious patterns detected.