ad-performance-analyzer

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides legitimate marketing optimization frameworks and benchmarks. No malicious patterns, hidden code, or unauthorized data access behaviors were identified.
  • [NO_CODE]: The skill consists entirely of markdown documentation and configuration metadata. It contains no executable scripts, binaries, or automated code execution logic.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes untrusted advertising metrics and campaign data. Ingestion points: User-provided performance metrics and campaign reports (README.md, SKILL.md). Boundary markers: Absent. Capability inventory: Use of analytical tools such as analyze_performance and ad-insights for data processing. Sanitization: Absent. This surface is inherent to the skill's primary purpose and does not escalate the safety verdict.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 05:55 AM