creator-vetting

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data (creator profiles and campaign briefs), creating an attack surface for indirect prompt injection.
  • Ingestion points: Creator profiles, campaign briefs, and shortlist criteria identified in SKILL.md.
  • Boundary markers: No specific delimiters are defined to isolate external data from instruction context.
  • Capability inventory: The skill is restricted to 'Read' and 'Write' tool access as specified in the frontmatter.
  • Sanitization: No data validation or sanitization is mentioned or performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 12:13 AM
Security Audit — agent-trust-hub — creator-vetting