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 setWebContentsDebuggingEnabled calls 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
Risk Level
SAFE
Analyzed
Mar 30, 2026, 03:34 PM
Security Audit — agent-trust-hub — android-webview-debug