appium-skill
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user requirements to generate automation code, which is an inherent attack surface for indirect prompt injection.
- Ingestion points: User-provided application details and test scenario descriptions in SKILL.md.
- Boundary markers: The skill does not implement specific delimiters or warnings to ignore instructions embedded in the mobile application metadata it might process.
- Capability inventory: The skill generates executable scripts in Java, Python, and JavaScript.
- Sanitization: There is no evidence of sanitization for user-provided data before it is interpolated into the generated code templates.
- [DYNAMIC_EXECUTION]: The skill's primary function is generating functional automation scripts for mobile platforms (Android and iOS). It uses well-documented templates for standard Appium clients like the Java client, Python client, and WebdriverIO.
Audit Metadata