The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected in the skill's instructions or logic. The skill's primary purpose is data analysis and reporting.- [REMOTE_CODE_EXECUTION]: No remote code execution patterns, such as piping network content to a shell, were found. All dependencies are internal reference files provided with the skill.- [DATA_EXFILTRATION]: No credential harvesting or unauthorized data exfiltration patterns were identified. Network operations are restricted to well-known app store domains (Apple and Google) and are used exclusively to fetch public listing data.- [PROMPT_INJECTION]: No direct prompt injection attempts or instructions to bypass safety filters were observed. The instructions are focused on guiding the agent through a structured auditing process.- [COMMAND_EXECUTION]: The skill does not perform any unauthorized command execution or privilege escalation. It uses standard tools like WebFetch for gathering information.- [SAFE]: The skill includes a surface for indirect prompt injection by processing external app descriptions and reviews; however, as the skill lacks exploitable capabilities (like code execution or file writes), the risk is negligible.

aso