ClawHub
Back to skill

Security audit

Scoro

Security checks for vulnerabilities and agentic risk

Overview

This Scoro skill appears purpose-built, but it gives an agent broad company data and mutation access through an API key sent to a configurable URL.

Install only with a dedicated least-privilege Scoro API key, verify SCORO_COMPANY_URL is exactly your HTTPS Scoro tenant API URL, and avoid enabling finance/contact/delete-capable permissions unless you intentionally want the agent to access or change those records. Treat team reports as sensitive employee data and require clear user authorization before using them.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:71
Finding

API Credential Can Be Transmitted to an Unrestricted Configurable Destination

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation text says to use the skill for 'any Scoro data,' which is overly broad and can cause the agent to invoke this integration for loosely related prompts. In practice, that increases the risk of unnecessary access to sensitive business records and of the model choosing this skill when a safer or narrower path would be more appropriate.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 4)May include surrounding context.

md
---
name: scoro
description: "Scoro API v2 integration for time tracking, task management, utilization reporting, team status reports, and billable corrections. Use when: user asks about Scoro tasks, time entries, hours (billable/non-billable), utilization reports, team status, or any Scoro data."
homepage: https://api.scoro.com/api/v2
metadata:
  {
    "openclaw":

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The standard prompts use broad natural-language triggers like 'show team status' and 'team pulse' without clear guardrails on whose data may be accessed or what authorization is required. This can lead to over-collection of employee time, utilization, and manager-reporting data, especially in environments where prompts are ambiguous or the requesting user should not have broad visibility.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 86)May include surrounding context.

Example Request (curl)

bash
curl -X POST "$SCORO_COMPANY_URL/timeEntries/list" \
  -H "Content-Type: application/json" \
  -d '{
    "apiKey": "'"$SCORO_API_KEY"'",

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill documentation expands scope from time tracking and reporting into many unrelated Scoro modules and explicitly mentions destructive operations like delete. That broadens the available action surface far beyond the declared purpose, increasing the chance an agent will perform sensitive or destructive actions against finance, contacts, orders, or other business data when a user only expected reporting/task support.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.