room-schema-governance

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the local Gradle wrapper (./gradlew :app:assembleDebug) to verify schema integrity. This is a standard and necessary operation for Android development and does not involve risky network calls or suspicious parameters.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project source files (entities) and has the capability to modify code and execute build scripts, creating a surface for indirect prompt injection. (1) Ingestion points: Modified or added classes annotated with @Entity. (2) Boundary markers: Absent; no markers are defined to isolate potential instructions in code comments. (3) Capability inventory: File modification of @Database classes and shell execution via gradlew. (4) Sanitization: Absent; entity content is not validated for malicious instructions before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 08:45 PM
Security Audit — agent-trust-hub — room-schema-governance