squad-frontend
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to process external, potentially untrusted data sources, creating a surface for indirect prompt injection.
- Ingestion points: SKILL.md and reference files identify Figma content, API payloads, external documentation, and browser research pages as primary inputs.
- Boundary markers: The instructions do not define specific structural delimiters for these inputs, though they establish conceptual trust boundaries.
- Capability inventory: The agent is authorized to modify local source code, interact with browsers, and manage local development processes (servers/watchers).
- Sanitization: The skill contains explicit defensive instructions to treat all external data as untrusted, verify claims against primary documentation, and ensure secrets are never exposed in logs or client code.
Audit Metadata