safha
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a legitimate data collection tool. No evidence of prompt injection, obfuscation, or persistence mechanisms was found.
- [EXTERNAL_DOWNLOADS]: The skill is designed to scrape web content from user-provided URLs or sitemaps. The examples provided target reputable news organizations (e.g., Al Jazeera, CNN, BBC Arabic), which is consistent with its stated purpose of building a high-quality Arabic text corpus.
- [COMMAND_EXECUTION]: The skill interacts with the local environment using the
safhaCLI tool. All command patterns shown are standard for data processing and do not involve privilege escalation, unauthorized file access, or suspicious subprocess spawning.
Audit Metadata