linkedin-automation
Warn
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADS
Full Analysis
- [Unverifiable Dependencies] (MEDIUM): The skill instructs the user to configure 'https://rube.app/mcp' as an MCP server. This domain is not included in the Trusted External Sources list, which represents an unverified third-party dependency providing the functional logic and tool schemas for the skill.
- [Indirect Prompt Injection] (LOW): The skill lacks necessary safeguards for handling external data. 1. Ingestion points: 'LINKEDIN_GET_MY_INFO' and 'LINKEDIN_GET_COMPANY_INFO' (File: SKILL.md). 2. Boundary markers: Absent; there are no instructions to use delimiters or ignore instructions within external data. 3. Capability inventory: 'LINKEDIN_CREATE_LINKED_IN_POST', 'LINKEDIN_CREATE_COMMENT_ON_POST', and 'LINKEDIN_DELETE_LINKED_IN_POST' (File: SKILL.md). 4. Sanitization: Absent; no input validation or escaping mechanisms are specified.
Audit Metadata