accessibility

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to perform build tasks and modify system-level configurations on connected Android devices.
  • Evidence: Execution of ./gradlew connectedDebugAndroidTest, ./gradlew lint, and adb shell settings put system font_scale 1.3 is defined in the validation section of SKILL.md.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it is designed to ingest and process potentially untrusted data from the user's workspace, such as UI labels and source code.
  • Ingestion points: As per SKILL.md, the skill inspects composables, UI states, labels, and error messages.
  • Boundary markers: The instructions do not define delimiters or explicit rules to disregard instructions embedded within the processed UI content.
  • Capability inventory: The skill has permissions to edit project files and execute shell commands, which could be abused if an injection is successful.
  • Sanitization: No sanitization or validation of the ingested content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 12:31 PM
Security Audit — agent-trust-hub — accessibility