squad-qa
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues detected. The skill follows security best practices for handling untrusted data and environment management.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which presents a potential injection surface. This is addressed by instructions to treat inputs as untrusted and redact secrets. 1. Ingestion points: Test data, logs, screenshots, network payloads, and issue text (SKILL.md). 2. Boundary markers: Explicit instruction to treat data as untrusted is present. 3. Capability inventory: Interaction with test runners (Playwright, Cypress, k6) which involves shell execution (SKILL.md). 4. Sanitization: Instruction to redact secrets and personal data is present.
Audit Metadata