Back to skill

Security audit

box-legal-workflows-ma

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Box deal-room workflow with sensible confirmation steps, but users should review its unpinned prerequisite installs and broad trigger wording.

Install this only if you intend to let an agent help manage Box deal-room content and permissions. Confirm every external collaborator, shared link audience, expiration, and folder scope before allowing changes, and prefer pinned or otherwise vetted versions of the prerequisite Box skills before use.

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
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger description is broad enough to activate on ordinary legal or business conversations about M&A, due diligence, or deal rooms, which can cause the agent to enter a high-impact workflow unexpectedly. In this context, accidental invocation is more sensitive because the skill can drive access-control changes, sharing actions, and AI processing over confidential deal documents.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The skill instructs users to install a dependency directly from a moving source via npx skills add without pinning a specific version or immutable commit. If the upstream package or repository is changed, compromised, or retagged, users could pull and execute unreviewed code or altered skill content in a high-trust workflow.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

This line also references installation of a skill from an unpinned source, creating a supply-chain risk identical to line 9. Because the instruction is embedded as a prerequisite, operators may execute it reflexively, increasing the chance of importing a compromised or unexpected dependency.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.