mobile-checkpoint

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE] (SAFE): The skill is composed entirely of a markdown documentation file (SKILL.md). No executable scripts (Python, JavaScript, Bash) or configuration files that could trigger automated execution were provided.
  • [COMMAND_EXECUTION] (SAFE): The markdown references standard development tools such as git and ./gradlew. These are used in the context of project maintenance and state recovery, posing no inherent security risk as described.
  • [INDIRECT_PROMPT_INJECTION] (SAFE): While the skill mentions importing state from JSON files (/mobile-checkpoint import), it is a documentation-only description without implementation. There is no active ingestion logic present to evaluate for sanitization or boundary markers.
  • [DATA_EXPOSURE] (SAFE): The workflow interacts with standard project files like AndroidManifest.xml and build.gradle.kts for local state tracking. No network-based exfiltration or access to sensitive user credentials (like SSH keys or AWS tokens) is suggested.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 08:25 PM