meta-ads-analyzer
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides purely instructional markdown content for a performance analysis workflow. It contains no executable scripts, system commands, or external network operations.
- [PROMPT_INJECTION]: No attempts to override agent behavior, bypass safety filters, or extract system prompts were detected. The instructions focus on the stated goal of ad analysis.
- [DATA_EXPOSURE_AND_EXFILTRATION]: There are no hardcoded credentials, access to sensitive file paths, or network tools that could facilitate data exfiltration. The allowed tools (Read, Glob, Grep) are limited to reading local files for analysis.
- [OBFUSCATION]: No encoded content, zero-width characters, homoglyphs, or hidden URL patterns were found in the text.
- [INDIRECT_PROMPT_INJECTION]: While the skill uses file-reading tools to ingest ad data, it lacks capabilities (like network access or command execution) that would allow an attacker to exploit the agent via malicious data content.
Audit Metadata