LinkedIn Automation
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data and user-supplied templates which are then used to perform actions via automated tools.
- Ingestion points: User-provided inputs including
Post content,Connection criteria,Message templates, andCampaign settingsdefined in the frontmatter and template sections. - Boundary markers: The skill lacks explicit boundary markers or instructions to the agent to disregard instructions embedded within the processed content or templates.
- Capability inventory: Access to tools
linkedin_post,linkedin_message,linkedin_analytics, andlinkedin_leadswhich allow for outbound network communication and data retrieval. - Sanitization: No validation or sanitization logic is specified for the interpolated variables (e.g.,
{{hook_line}},{{message}}) before they are passed to the LinkedIn tools.
Audit Metadata