android-compose-xml-interoperability

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill references local execution of Gradle build tasks (./gradlew) and a Python script (scripts/eval_triggers.py) to validate UI components. These are standard development workflows for Android projects.
  • [EXTERNAL_DOWNLOADS]: Contains links to official Android developer documentation (developer.android.com), which is a well-known and trusted source for technical guidance.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface (Category 8) as it processes user-provided UI requirements to trigger build and evaluation commands. Evidence Chain: (1) Ingestion points: User prompts matching triggers in SKILL.md. (2) Boundary markers: Absent. (3) Capability inventory: Subprocess execution of Gradle and Python scripts as documented in scripts/run_examples.sh and references/scenarios.md. (4) Sanitization: No explicit sanitization or input validation is demonstrated in the provided configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 12:40 PM