ClawHub
Back to skill

Security audit

Roi Incremental Tracking

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local ROI tracker that writes expected ledger and report files in the workspace, with no evidence of exfiltration, hidden persistence, or privilege escalation.

Install only if you want the agent to maintain a local ROI ledger in your workspace. The data may include costs, hourly rates, cash amounts, evidence links, and notes, so treat <workspace>/reports/roi/ as business-sensitive. The referenced dashboard script is missing from this artifact, so dashboard generation may not work unless supplied separately.

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)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The activation guidance is broad enough to trigger on generic requests to 'measure, log, or close out' ROI/value, without clear exclusions or confirmation boundaries. In practice this can cause the agent to invoke the skill in situations the user did not intend, leading to unintended creation or modification of ROI tracking data and possible misattribution of financial metrics.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill directs the agent to create, copy, archive, and regenerate files under the workspace, including CSV, JSON, HTML, and a Python script, without explicitly requiring prior user notice or confirmation. This is risky because users may not expect persistent filesystem changes from a conversational ROI request, and automatic writes can overwrite, clutter, or expose sensitive business tracking data.

Static analysis

No suspicious patterns detected.