design-test-gate

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands for validating Android project health, including ./gradlew assembleDebug, ./gradlew test, and npm run check.
  • [EXTERNAL_DOWNLOADS]: The documentation references external companion skills from aldefy and skydoves. While the skill does not automate their installation, these references point to external sources not identified as trusted vendors.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it processes untrusted data from the local environment to drive its internal logic.
  • Ingestion points: The skill reads Gradle build files, CI workflow logs, and build/test failure reports as specified in SKILL.md and references/design-test-gate-notes.md.
  • Boundary markers: There are no explicit delimiters or specific instructions for the agent to treat these external inputs as non-executable or untrusted data.
  • Capability inventory: The agent has the capability to run shell commands (gradlew, npm) and invoke other skills based on the results of the ingested data.
  • Sanitization: The instructions do not define any sanitization, filtering, or validation steps for the content of the logs or project files before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 12:30 PM
Security Audit — agent-trust-hub — design-test-gate