ClawHub
Back to skill

Security audit

Credit

Security checks for vulnerabilities and agentic risk

Overview

This is a credit-education skill with disclosed prompts and no executable code, though users should avoid sharing identifying financial details.

Install only if you want general credit education and planning help. Do not paste full credit reports, SSNs, account numbers, addresses, login details, or unredacted documents; use rounded balances, utilization percentages, dates, and non-identifying summaries instead. Treat its advice as educational, especially before major borrowing or dispute decisions.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (3)

Self-Modification

High
Category
Rogue Agent
Content
# Credit Skill — Heartbeat

*Proactive credit health monitoring. Run these checks on schedule.*
Confidence
85% confidence
Finding
Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The example explicitly invites the user to share current balances and account-level financial details, which can lead users to disclose sensitive personal financial information in a chat context without any warning about privacy, redaction, or minimization. In a credit-management skill, this risk is heightened because users may also reveal account numbers, payment history, collections, or other highly sensitive data that could be misused or unnecessarily retained.

Vague Triggers

Medium
Confidence
90% confidence
Finding
This manifest file defines many generic trigger phrases such as "credit score," "credit report," and "credit card" without clarifying whether they are exact invocation phrases, examples, or bounded to a specific context. Because there are no exclusion conditions or negative examples, the skill could be invoked during ordinary conversation about personal finance rather than only when the user intends to use this skill.

Static analysis

No suspicious patterns detected.