linkedin-automation
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection. 1. Ingestion points: Data entering via LINKEDIN_GET_MY_INFO and LINKEDIN_GET_COMPANY_INFO tools. 2. Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the documentation. 3. Capability inventory: The skill is documented as having the capability to create and delete posts and comments on LinkedIn. 4. Sanitization: No sanitization or validation of external LinkedIn content is specified.
- [EXTERNAL_DOWNLOADS]: The skill documentation instructs users to connect to an external Model Context Protocol (MCP) server at https://rube.app/mcp. This is required for the skill's primary purpose and does not involve executing arbitrary remote code.
- [SAFE]: No malicious patterns, hardcoded credentials, or obfuscated content were detected in the skill's instructions.
Audit Metadata