meta-ads-campaign-builder

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified in the skill instructions. The content is focused on marketing strategy and campaign structure.
  • [NO_CODE]: This skill is composed entirely of markdown documentation and YAML metadata. It does not include any scripts, binaries, or configuration files that execute logic on the local system.
  • [DATA_EXFILTRATION]: No exfiltration vectors were found. The skill does not access sensitive local files or transmit user data to external endpoints.
  • [PROMPT_INJECTION]: There are no attempts to override agent behavior, bypass safety guidelines, or extract system prompts. The instructions are domain-specific to Meta Ads.
  • [SAFE]: The skill has a surface for indirect prompt injection (Category 8) as it ingests data from web searches (Phases 1C and 2A). However, it lacks high-risk capabilities and uses the information solely for text-based campaign planning, resulting in a safe assessment.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 10:48 AM