Security audit

Deal Desk

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown deal-desk playbook that can influence pricing and approval advice but does not request system access or perform hidden actions.

Use this as an advisory framework for deal review, not as authority to finalize discounts, legal terms, or approvals without your organization's normal finance, legal, and management controls. The included external links appear to be optional commercial resources.

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

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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)

Autonomous Decision Making

Medium

Category: Excessive Agency
Content: ### 4. Approval Workflow ``` AE submits deal → Deal Desk reviews (same day) → IF standard terms + approved discount: Auto-approve IF non-standard: Route to approver chain → Finance review (margin check) → Legal review (if custom terms) →
Confidence: 85% confidence
Finding: Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.