linkedin-engagement-handler

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted user-generated content from external sources.
  • Ingestion points: The skill ingests LinkedIn comments and reactions as described in SKILL.md.
  • Boundary markers: No explicit boundary markers or delimiters are defined to separate untrusted data from instructions, nor are there warnings for the agent to ignore embedded commands.
  • Capability inventory: The skill possesses significant capabilities, including CRM record updates via {{CRM_HYGIENE_SKILL}}, automated Slack notifications to {{ENGAGEMENT_CHANNEL}}, and queueing LinkedIn connection requests.
  • Sanitization: No sanitization, filtering, or validation processes are specified for the external comment text before it is used for outreach generation or logging.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 04:39 PM
Security Audit — agent-trust-hub — linkedin-engagement-handler