sparkscan-android

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves the latest SDK version metadata from Maven Central (central.sonatype.com), a well-known service for Android library distribution, to ensure the project uses up-to-date dependencies.
  • [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves reading and acting upon the content of local project files, creating a potential surface for indirect prompt injection attacks.
  • Ingestion points: The agent reads the project's build.gradle, gradle/libs.versions.toml, and Kotlin/Java source files to determine the current SDK state and apply migration logic.
  • Boundary markers: The skill does not provide specific instructions to the agent to treat local file content as untrusted data or to ignore instructions embedded within it.
  • Capability inventory: The skill utilizes the agent's ability to read from and write to the local file system to automate the integration process.
  • Sanitization: No sanitization or verification logic is applied to the content extracted from the project files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:35 PM
Security Audit — agent-trust-hub — sparkscan-android