ClawHub
Back to skill

Security audit

Commercial Credit Memo Drafter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent draft-writing aid for commercial credit memos, with clear review labels and no hidden execution or persistence behavior.

Install only for authorized commercial credit drafting workflows. Users should avoid entering borrower or guarantor data unless they are allowed to process it in their agent environment, and final credit, KYC, OFAC, BSA/AML, and policy decisions should remain with qualified human reviewers.

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 (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill description is broadly phrased to activate whenever a user needs help turning borrower financials and a loan request into a credit memo, without clear exclusions or tighter trigger criteria. In agent environments, over-broad activation can cause the skill to be invoked on adjacent financial, compliance, or credit-decision tasks, increasing the chance of inappropriate data handling, policy misuse, or unreviewed recommendations in a regulated workflow.

Static analysis

No suspicious patterns detected.