skills/karnonson/marketing-skills/ads/Gen Agent Trust Hub

ads

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were identified in the skill's instructions, scripts, or reference materials. The skill follows performance marketing best practices and uses standard code snippets for conversion tracking and API integration.
  • [PROMPT_INJECTION]: Potential surface for indirect prompt injection. The skill is designed to analyze external data sources such as performance reports and marketing context files. It lacks explicit instructions to disregard potential commands embedded within the data (boundary markers), which could theoretically allow crafted inputs to influence the agent's output. However, this is a common and low-risk pattern for data-processing skills.
  • Ingestion points: references/ad-creative-guidelines.md (performance reports) and SKILL.md (marketing context).
  • Capability inventory: Generation of ad copy, campaign structures, and marketing strategies.
  • Boundary markers: None identified.
  • Sanitization: Not explicitly performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 05:32 AM
Security Audit — agent-trust-hub — ads