ClawHub
Back to skill

Security audit

catchup

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a transparent catchup workflow for summarizing recent repository, document, and log changes, with no evidence of hidden execution, persistence, or data exfiltration.

Before installing, be aware that this skill may activate for general requests like status or summary and can lead the agent to inspect repository, document, or log context. Use it with clear scope, such as a specific branch, date range, project, or log file.

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 (2)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.

md
**Git**: Load `modules/git-catchup-patterns.md` for git commands. Consider `sanctum:git-workspace-review` for initial data gathering.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill advertises very broad activation terms such as 'summary', 'status', 'progress', and 'context', plus generic cues like 'get me up to speed'. In an agent ecosystem, this can cause accidental or overly frequent invocation in normal conversation, leading the agent to gather repository or document context when the user did not explicitly intend to invoke this skill, increasing data exposure and workflow confusion.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.