israeli-aso
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a Python script
scripts/keyword_analyzer.pyintended for execution by the agent. - The script is a utility for string manipulation, specifically for de-duplicating and calculating the length of Hebrew keyword lists.
- Technical analysis shows the script uses only the standard library
argparseand does not perform file system operations, network requests, or dynamic code execution. - [EXTERNAL_DOWNLOADS]: The skill references several external URLs for documentation and evidence.
- All referenced domains (e.g.,
developer.apple.com,support.google.com,gs.statcounter.com) are well-known, official services or reputable information sources related to the skill's primary purpose. - These references are purely informational and do not involve the download of executable code, configuration scripts, or binary payloads.
- [PROMPT_INJECTION]: The instructions in
SKILL.mdandSKILL_HE.mdprovide guidance on ASO best practices for the Israeli market. - No attempts to override agent behavior, bypass safety filters, or extract system prompts were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided keywords via the
keyword_analyzer.pyscript. - Ingestion point: The agent is instructed to pass user keywords as command-line arguments to the script.
- Capability inventory: The script lacks the capability to perform network operations, file writes, or command execution on the processed data.
- The data is treated as literal strings for analysis purposes only.
- [REMOTE_CODE_EXECUTION]: No remote code execution patterns or package installations were found.
- [DATA_EXFILTRATION]: No data exfiltration patterns, hardcoded credentials, or sensitive file path access were detected.
- [OBFUSCATION]: No obfuscated code, hidden characters, or encoded URLs were found.
Audit Metadata