daily-auditor
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were found. The skill is designed strictly for read-only analysis of advertising metrics.
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to run an audit using a Meta Ads MCP. The instructions explicitly mandate a 'READ-ONLY' context and prohibit the agent from making any changes to the account.
- [EXTERNAL_DOWNLOADS]: The skill metadata references the author's official documentation site (kelpi.ai). This is a legitimate vendor resource and does not involve the execution of untrusted code.
- [PROMPT_INJECTION]: The skill processes external data from Meta Ads accounts, creating a potential surface for indirect prompt injection. However, the skill lacks the high-risk capabilities (such as file-write or shell execution) that would make such an injection exploitable, and it includes instructions to strictly use account numbers without estimation.
Audit Metadata