paid-ads-specialist
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and does not include any scripts, commands, or executable code.
- [CREDENTIALS_UNSAFE]: The skill contains proactive security instructions to prevent the exposure of sensitive information such as ad account IDs, billing details, and API tokens.
- [DATA_EXFILTRATION]: No network access or data transmission mechanisms are present in the instructions.
- [PROMPT_INJECTION]: The instructions follow a standard persona-based format without any attempts to bypass safety filters or override system constraints.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing external data such as campaign briefs and landing pages. While this represents an ingestion surface for untrusted data, the skill lacks dangerous capabilities (like shell execution or file writing) that could be exploited via injection.
Audit Metadata