Back to skill

Security audit

Zoom Cli

Security checks for vulnerabilities and agentic risk

Overview

ClawScan labels this Zoom CLI skill benign, with medium confidence; the main caveat is that its documented search and contact lookup reach beyond the meeting-focused purpose, and inspection was partial.

The verdict is benign, but consider whether you want the skill to search mail, notes, broader chat and documents, or general Zoom contact directories. Skillspector inspected all seven listed components but marked coverage partial because two local references could not be resolved; treat the assessment as incomplete.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Search capabilities extend beyond Zoom meetings to mail, notes, and non-meeting chat and documents.

Medium
Category
Excessive Agency
Confidence
97% confidence
Finding

The manifest limits the skill to the owner's Zoom meetings and associated transcripts, summaries, meeting chat, recordings, and scheduling. However, L51–L53 expose explicitly selectable messages, mail, and notes searches, while L60–L61 describe live searches of additional Zoom chat and documents; these capabilities retrieve content outside the declared meeting-focused scope.

Content

No source excerpt is available for this finding.

The skill exposes live company and external contact-directory access beyond its stated meeting-focused purpose.

Medium
Category
Excessive Agency
Confidence
92% confidence
Finding

L26–L27 document commands for listing company and external Zoom contacts and looking up contacts by ID or email. The manifest describes meeting research, recordings, preparation, authentication, and meeting management, but does not authorize general contact-directory browsing or constrain these lookups to participants in relevant meetings.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · references/prepare.md (reported line 63)May include surrounding context.

md
- Only use communications IDs explicitly configured for the selected profile through
  `zm personal config set context.sources`. A grant covers one whole message or mail account or document folder; do
  not broaden scope for an agent. `zm personal config show` reveals the configured selections.
- A document folder uses provider `local` (a plain folder) or `obsidian` (a vault) and account `notes:<folder-id>`
  from `memo folders list`.
- `meetings prepare <series-id> --context-source <id> --context-query '<words>'` adds cited literal matches. Repeat