voiceover

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to automate development workflows, including workspace isolation and pull request management.
  • Employs git worktree add to create isolated development directories outside the current project root.
  • Uses gh pr create to automate the creation of pull requests on GitHub.
  • Executes pnpm fraimz for project scaffolding and running automated proof checks.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided feature descriptions as the basis for generating demo scripts and scaffolding code.
  • Ingestion points: User-provided feature requests and script iterations in Phase 1.
  • Boundary markers: None explicitly defined to separate user input from the rest of the prompt context.
  • Capability inventory: The skill has capabilities to write files (evals/voiceovers/), execute shell commands (git, gh, pnpm), and push code to remote repositories.
  • Sanitization: No explicit sanitization or validation of the input feature description is defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 03:33 AM