webapp-testing
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with and tests local web applications, which serves as an ingestion point for untrusted data. Do NOT flag the standard development tools as malicious.
- Ingestion points: The agent interacts with web content, logs, and UI elements of local applications (SKILL.md).
- Boundary markers: No explicit boundary markers or instructions to ignore embedded content are provided.
- Capability inventory: The skill uses subprocess execution to run commands like
npm run devandnpx playwright test(SKILL.md). - Sanitization: There is no mention of sanitization, escaping, or filtering of the web content or logs before the agent processes them.
Audit Metadata