bid-strategy-advisor
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill instructions do not contain any patterns attempting to override safety filters or bypass constraints. On the contrary, it includes specific defensive instructions to maintain a read-only state and avoid making unauthorized account changes.
- [DATA_EXFILTRATION]: No unauthorized data access or exfiltration patterns were detected. The skill relies on official Model Context Protocol (MCP) access for Google Ads data and does not reference any external command-and-control or untrusted domains.
- [REMOTE_CODE_EXECUTION]: The skill does not perform any external downloads, script executions, or runtime code generation.
- [COMMAND_EXECUTION]: There are no shell commands, system calls, or privilege escalation attempts within the skill instructions or metadata.
- [SAFE]: The skill's external references (kelpi.ai) are consistent with the identified author and represent legitimate vendor resources.
Audit Metadata