android
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The documentation provides installation commands that fetch the skill suite and its sub-modules from a remote GitHub repository (
hereisderek/derek-agent-skills). - [COMMAND_EXECUTION]: The
mobile-orchestration-preset.mdfile defines various shell commands for environment hooks and validation sequences. - Executed commands include Android build tools (
./gradlew), Android Debug Bridge (adb) for device interaction, and the execution of a local shell script (device-pool.sh) located within the skill's root directory. - [INDIRECT_PROMPT_INJECTION]: The 'PR Quiz' module indicates that the skill processes content from GitHub Pull Requests, creating a potential attack surface for instructions embedded in external data.
- Ingestion points: Pull Request content and metadata processed by the PR Quiz module (referenced in
SKILL.md). - Boundary markers: No specific delimiters or warnings for the agent to ignore instructions within the PR data were identified in the provided files.
- Capability inventory: The skill environment has access to shell execution, including project build commands and device management via
adb(documented inmobile-orchestration-preset.md). - Sanitization: No mention of input validation or sanitization for external PR data is present.
Audit Metadata