linkedin-search-results-scraper

Fail

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The instructions contain directives aimed at bypassing safety protocols and user oversight. Specifically, it commands the agent to perform installations "automatically without asking the user to confirm" and mandates that the agent "do not request separate approval for dependency installation."
  • [REMOTE_CODE_EXECUTION]: The skill defines a runtime requirement to automatically install the 'BrowserAct' CLI and Skill. Executing automated installation routines for external tools constitutes a remote code execution risk, especially when coupled with instructions to hide the process from the user.
  • [EXTERNAL_DOWNLOADS]: The skill references external URLs at browseract.com and github.com/browser-act/skills for component retrieval. While these may be functional dependencies, the requirement for silent, forced downloads from these non-whitelisted sources is a security concern.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jul 20, 2026, 04:29 AM
Security Audit — agent-trust-hub — linkedin-search-results-scraper