ClawHub
Back to skill

Security audit

FP&A Engine

Security checks for vulnerabilities and agentic risk

Overview

This is a finance-analysis instruction skill that asks for sensitive business data, but the access is purpose-aligned and there is no executable code, persistence, or hidden data movement.

Install only if you are comfortable sharing company financial information with your agent. Provide the minimum data needed, redact account numbers and employee identifiers where possible, and treat generated board or fundraising materials as drafts for human review.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The README tells the agent to act on very broad natural-language requests such as building financial models, analyzing P&L data, and preparing board packages, but it does not define clear activation boundaries, input requirements, or safety constraints. In an agent ecosystem, this can cause over-triggering or invocation in contexts the user did not intend, potentially leading to inappropriate handling of sensitive financial data or overly autonomous actions based on ambiguous prompts.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly solicits highly sensitive business and personnel data including cash on hand, payroll data, bank statements, fundraising details, and headcount information, but provides no warning about confidentiality, minimization, or secure handling. This increases the risk of oversharing, unnecessary collection, and exposure of financially material or private information in routine interactions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The command triggers are very broad and overlap with ordinary finance-related user requests such as 'Analyze our P&L', 'Budget review', and 'Forecast revenue'. In an agent environment, this can cause unintended or overly eager activation, leading the skill to ingest or operate on sensitive financial data when the user did not explicitly intend to invoke this capability.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.