ads-meta
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- NO_CODE (SAFE): The skill consists exclusively of markdown instructions and does not include any executable scripts (Python, Node.js, or Shell). All logic is handled through natural language processing of the provided criteria.
- DATA_EXPOSURE (SAFE): While the skill discusses processing sensitive marketing data (Email, Phone, Names) for Meta's Conversions API (CAPI) matching, it does not contain any code or instructions to exfiltrate this data or send it to unauthorized third parties. It describes standard advertising platform parameters.
- PROMPT_INJECTION (SAFE): No patterns of prompt injection, instruction overrides, or safety bypass attempts were detected in the skill text or metadata.
- EXTERNAL_DOWNLOADS (SAFE): No external URLs or remote dependencies are referenced. All file references (e.g.,
ads/references/meta-audit.md) point to local paths within the skill's own structure.
Audit Metadata