openspec-verify

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes standard development commands including openspec, codegraph, rg, and ./gradlew. These are used for their intended purposes: managing project status, exploring code symbols, searching files, and running build/test tasks.
  • [DATA_EXPOSURE]: The skill interacts with local project files and build artifacts (HTML/XML reports) generated by Gradle. It does not attempt to access sensitive system directories like SSH keys or cloud credentials.
  • [REMOTE_CODE_EXECUTION]: The skill uses the local Gradle wrapper (./gradlew) found within the project root. This is standard practice for Android projects and does not involve downloading or executing arbitrary scripts from untrusted external domains.
  • [PROMPT_INJECTION]: The instructions follow a structured workflow for verification and do not contain patterns designed to bypass safety filters or override system-level constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 05:52 PM
Security Audit — agent-trust-hub — openspec-verify