linkedin-cli

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install a global NPM package @linkedapi/linkedin-cli to provide the core command-line functionality needed for LinkedIn automation.
  • [COMMAND_EXECUTION]: The skill extensively uses shell command execution to run the linkedin CLI tool for all operations, including account setup, data retrieval, and account actions.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its data ingestion and execution flow:
  • Ingestion points: Untrusted content is ingested from the external LinkedIn environment (e.g., profiles via linkedin person fetch, messages via linkedin message get, and posts via linkedin post fetch).
  • Boundary markers: The instructions lack explicit boundary markers or delimiters to isolate fetched LinkedIn content from the agent's logic, which may lead the agent to follow instructions embedded in that content.
  • Capability inventory: The skill provides powerful capabilities like linkedin message send, linkedin connection send, and linkedin post create. These could be misused if the agent is manipulated by malicious data fetched in a previous step.
  • Sanitization: There are no documented steps for sanitizing or validating external data before it enters the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 09:08 PM
Security Audit — agent-trust-hub — linkedin-cli