Security audit

LinkedIn Automation by Linked API

Security checks for vulnerabilities and agentic risk

Overview

The skill matches its LinkedIn automation purpose, but it should be reviewed carefully because it uses account tokens and a global third-party CLI to perform live LinkedIn actions without enough safety scoping.

Install only if you are comfortable letting a third-party Linked API cloud browser act on your LinkedIn account. Treat both tokens as secrets, avoid entering them in chat or command history, revoke and rotate them if exposed, pin and audit the CLI before use, and require explicit confirmation before any message, post, comment, reaction, connection change, company-page action, or custom workflow.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:12
Finding: Unpinned Global Installation of a Third-Party CLI Package
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:18
Finding: Authentication Tokens Exposed Through Command-Line Arguments
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The authentication section instructs users to provide a Linked API Token and Identification Token without explicitly warning that these are sensitive credentials that can grant account access and automation capability. In a tool/agent context, this can lead users to paste secrets into insecure channels or logs, enabling account compromise or unauthorized actions.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill explicitly enables sending messages and InMails to real LinkedIn users but does not clearly warn that these are live outbound actions against external parties. That omission increases the risk of accidental spam, unauthorized outreach, reputational harm, and policy-violating use by an agent or user who assumes the commands are only draft or simulated operations.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: These commands perform live state-changing actions on a LinkedIn account, including posting, commenting, reacting, and managing connections, but the documentation does not clearly emphasize that the effects are real and may be difficult to undo completely. In an agent setting, this raises the likelihood of unintended account changes, public posts, social graph changes, and reputational or compliance issues.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.