android-webview-debug
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes automated search and file modification tools to identify and replace
setWebContentsDebuggingEnabledcalls within the local Android project. - [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingest and processes untrusted source code data from the project. 1. Ingestion points: Java and Kotlin source files are read during the grep and classification steps. 2. Boundary markers: No delimiters or explicit safety instructions are used to isolate the codebase content from the agent's logic. 3. Capability inventory: The skill has the ability to read project files, overwrite code, and create or delete local configuration files. 4. Sanitization: No sanitization or validation of the input source code is performed before it is used to determine modification logic.
Audit Metadata