LinkedIn Automation

Pass

Audited by Gen Agent Trust Hub on Jun 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface due to automated messaging and engagement features.
  • Ingestion points: The workflow processes external LinkedIn comments and profile data (e.g., names, interests) for automated interpolation into templates.
  • Boundary markers: Outreach and response templates lack delimiters or boundary markers to isolate untrusted external data from the surrounding instructions.
  • Capability inventory: The skill utilizes the linkedin_post and linkedin_message tools to publish and transmit content.
  • Sanitization: No evidence of validation or filtering for external input is provided before it is used in outbound communications.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 3, 2026, 02:52 PM
Security Audit — agent-trust-hub — LinkedIn Automation