edit-app

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • Command Execution: The skill utilizes the Bash tool to perform environment diagnostics, run the TypeScript compiler (tsc), and execute project scripts (e.g., check-routes.js, offline-profile-delta.js). These operations are constrained to the local project directory and are part of the skill's intended functionality as a development tool.
  • External Package Management: The skill manages Node.js dependencies using npm install --save-exact. To mitigate potential risks associated with external code, the skill follows a safety protocol of using an approved exact-version dependency table and requires explicit user consent before installation.
  • Indirect Prompt Injection Surface: The skill processes external data including user-provided prompts and existing application source code, which are then used to influence the actions of secondary agents (e.g., screen-builder). The skill implements structured prompting and manual approval gates to manage the risk of instructions embedded within the processed data.
  • Automated Quality Gates: The workflow enforces several verification steps, including schema validation and color contrast checks, ensuring that modifications meet project standards before being finalized.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 10:39 AM
Security Audit — agent-trust-hub — edit-app