ads-audit

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill instructions are limited to data analysis and reporting workflows consistent with its stated purpose. No malicious patterns or unauthorized data access attempts were found.
  • [NO_CODE]: No executable scripts or code files are included in the skill. The analysis is based on markdown instructions and metadata, which significantly limits the attack surface.
  • [PROMPT_INJECTION]: The skill defines a process for ingesting external data (ad platform exports and reports). While this creates a theoretical surface for indirect prompt injection, the lack of executable capabilities and the descriptive nature of the skill render this risk minimal.
  • Ingestion points: Ad platform exports, search term reports, and screenshots from Google, Meta, LinkedIn, TikTok, and Microsoft Ads.
  • Boundary markers: The instructions do not define specific delimiters for separating external data from system instructions.
  • Capability inventory: No code or system tools are accessible through this skill.
  • Sanitization: No explicit sanitization or validation of the external data is described in the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 01:29 AM