sales-trigify

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious instructions, hidden code, or unauthorized network operations were found in the skill files. All external links and package references belong to the legitimate vendor or well-known technology services.
  • [PROMPT_INJECTION]: The skill is designed to process untrusted data from LinkedIn posts, profiles, and comments via the Trigify platform, which represents an indirect prompt injection surface. \n
  • Ingestion points: LinkedIn listening searches and profile monitoring (SKILL.md, references/platform-guide.md). \n
  • Boundary markers: The skill does not implement explicit delimiters or instructions for the agent to ignore potentially malicious embedded content within the ingested social signals. \n
  • Capability inventory: The platform includes capabilities for outbound HTTP requests and automated write operations to CRMs (HubSpot, Attio, Apollo) and outreach sequences (Instantly, Smartlead) (references/platform-guide.md). \n
  • Sanitization: No sanitization, validation, or filtering of external content is specified in the skill's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 12:21 AM
Security Audit — agent-trust-hub — sales-trigify