ad-format-fit

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions in SKILL.md define an interactive interview process that ingests untrusted user data.
  • Ingestion points: The 13-question interview section where users provide campaign objectives, budget, and business details.
  • Boundary markers: The instructions lack specific delimiters or system directives to isolate this user-provided text from the agent's logic.
  • Capability inventory: The skill is limited to providing textual reports and does not have access to sensitive file operations, network requests, or shell execution.
  • Sanitization: No data validation or escaping mechanisms are described.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 03:32 PM
Security Audit — agent-trust-hub — ad-format-fit