ClawHub
Back to skill

Security audit

Catalyst Calendar

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed trading-calendar helper that stores and updates catalyst events locally, with no executable code or hidden behavior found.

Install this if you want a local market catalyst calendar. Review sources and calendar updates before trading on them, and only enable the weekly or daily cron-style workflow if you want recurring scans and persistent local updates.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill's trigger scope is overly broad because it claims applicability to 'any asset class' and several loosely defined use cases without clear invocation boundaries. In an agentic environment, this can cause the skill to be selected in contexts where it may perform unnecessary market scanning or decision-support actions beyond the user's intended scope, increasing the chance of inappropriate automation or misleading trading context.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill instructs the agent to update a local JSON file but does not explicitly warn that this modifies persistent user data. In a tool-using agent, silent file writes can surprise users, create unwanted state changes, or be chained with broader triggers to make autonomous modifications the user did not clearly authorize.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.