app-qa-sweep
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to systematically ingest and analyze application source code, routing configurations, and API endpoints to perform a full-app sweep. Since the skill also possesses the ability to modify source code and execute shell-based build/test commands, it presents an attack surface for indirect prompt injection if the codebase being audited contains malicious instructions designed to manipulate the agent.
- Ingestion points: The skill reads application files such as
app/**/page.tsx, router configurations, and API route handlers during the inventory phase. - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions embedded within the application data it analyzes.
- Capability inventory: The skill is authorized to perform code fixes, execute
npm run build, run linting/type-checking tools, and trigger Playwright-based automated testing. - Sanitization: The instructions do not specify any sanitization, filtering, or validation steps for the content retrieved from the application files before it is processed by the agent's logic.
Audit Metadata