ClawHub
Back to skill

Security audit

Linkedin Ads CLI

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to be a coherent LinkedIn marketing integration, with expected access to ad analytics and lead data but no evidence of hidden or destructive behavior.

Install only if you intend to let the agent work with authorized LinkedIn Marketing data. Use least-privileged credentials, avoid fetching lead submissions unless needed, filter by account/form/date where possible, and avoid displaying unnecessary personal information.

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 (2)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly enables retrieval of lead form submissions, which can contain personal data, but it provides no user-facing privacy warning, consent check, or minimization guidance. In this context, the omission increases the risk that an agent will fetch and expose sensitive lead information more broadly than the user intended.

Scope Creep

Low
Category
Excessive Agency
Content
Default metric fields (when `--fields` is not specified): `impressions`, `clicks`, `costInLocalCurrency`, `costInUsd`, `externalWebsiteConversions`, `likes`, `comments`, `shares`, `follows`, `videoViews`

The CLI passes `--fields` and `--pivot` values directly to the LinkedIn API without validation. Additional fields and pivot values beyond the documented defaults may be available. Refer to the [LinkedIn Ad Analytics API docs](https://learn.microsoft.com/en-us/linkedin/marketing/integrations/ads-reporting/ads-reporting) for the full list.

### Audiences & targeting
Confidence
88% confidence
Finding
The skill states that --fields and --pivot are passed directly to the LinkedIn API without validation and that additional undocumented values may be available. This expands the reachable API surface beyond the documented safe subset, which can lead to overcollection of data, unexpected sensitive fields, or use of unreviewed API behaviors.

Static analysis

No suspicious patterns detected.