branded-content

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted data from user-provided marketing briefs which could be used to deliver indirect instructions to the agent. * Ingestion points: User-provided brief (SKILL.md). * Boundary markers: Absent. * Capability inventory: File writing to the local workspace (SKILL.md). * Sanitization: No sanitization or validation of the brief content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 07:35 AM
Security Audit — agent-trust-hub — branded-content