referrals

Pass

Audited by Gen Agent Trust Hub on Sep 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is purely informational, providing marketing frameworks, checklists, and email templates across all files. It does not include any scripts, executable code, or command-line instructions.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read local context files such as product-marketing.md in SKILL.md. This ingestion point lacks explicit boundary markers or sanitization for the external data. However, the skill capability inventory shows no high-risk tools such as network access, file writing, or command execution, rendering the surface non-exploitable within this skill's scope.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 11:20 AM