israeli-social-content
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides detailed instructional content for social media marketing. All referenced scripts and files are localized to the stated purpose of Israeli social content creation.
- [NO_CODE]: The bundled Python script (
scripts/posting_scheduler.py) is a simple utility that prints static scheduling information to the console. It performs no network operations, file system modifications, or sensitive data access. - [DATA_EXPOSURE_SAFE]: All external URLs provided in the documentation and
evidence.jsonpoint to well-known social media platforms (Facebook, Instagram, TikTok, LinkedIn) or reputable data sources (DataReportal, StatCounter, NapoleonCat). No sensitive local data is accessed or exfiltrated. - [OBFUSCATION_SAFE]: The skill mentions Unicode control characters (RLI, PDI, RLM, LRM) in the context of fixing Right-to-Left (RTL) formatting issues in Hebrew captions. This is a legitimate technical instruction for the domain and does not constitute malicious obfuscation.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes user-provided topics to generate social media content, it lacks high-privilege capabilities (like arbitrary command execution or network access) that could be exploited via injection. The risk of indirect prompt injection is negligible.
Audit Metadata