skills/albertmartorell1975/android-ai-workflow-foundation/play-billing-library-version-upgrade/Gen Agent Trust Hub
play-billing-library-version-upgrade
Warn
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands via
./gradlewto perform project synchronization, build the application (assembleDebug), and run unit tests. These actions are aligned with the skill's primary purpose of verifying library migrations. - [EXTERNAL_DOWNLOADS]: References official migration guides and release documentation from
developer.android.com. This domain is a well-known technology service and trusted source for Android-related content. - [PROMPT_INJECTION]: The skill exhibits deceptive metadata by claiming to be authored by 'Google LLC' and referencing official 'android' GitHub repositories, while the actual provider is identified as 'albertmartorell1975'. This impersonation is a deceptive practice that may cause users to incorrectly assume the skill is an official, vetted tool.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted local data to drive its logic.
- Ingestion points: Phase 1 and Phase 3 involve reading local build configuration files (
build.gradle,build.gradle.kts,libs.versions.toml) and application source code. - Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands within the ingested files.
- Capability inventory: The agent is authorized to execute shell commands and modify local files, creating a risk if malicious instructions are present in the ingested code.
- Sanitization: No sanitization or validation is performed on the content of the project files before they are processed by the agent.
Audit Metadata