ClawHub
Back to skill

Security audit

Biz Reporter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed business-reporting helper that may access sensitive company metrics, but its behavior is coherent with that purpose and no hidden or executable payload was found.

Install only if you intend the agent to use authorized business accounts for reporting. Configure credentials through secure environment variables, limit connected sources to the reports you actually need, confirm any scheduled cron jobs, and verify Slack, email, Notion, or Discord destinations before sending reports externally.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill description includes many broad, conversational trigger phrases such as 'how are we doing', 'show me our metrics', and 'compare this month to last month', which can overlap with ordinary user requests and cause the skill to activate in contexts the user did not explicitly intend. Because the skill can access sensitive business systems and generate outbound reports, overly broad routing increases the chance of unintended data access or disclosure through accidental invocation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill describes access to GA4, Stripe, social media, CRM, Airtable, and delivery to Slack, email, and Notion, but does not clearly warn users that using the skill may access stored credentials, query sensitive business data, and transmit summaries to external destinations. In a business-intelligence context, this omission is risky because users may not realize a casual request could trigger cross-system data aggregation and outbound sharing.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.