form-audit
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides legitimate instructions for UI and UX auditing. No evidence of obfuscation, malicious persistence, unauthorized data exfiltration, or credential harvesting was found within the skill files or metadata.
- [PROMPT_INJECTION]: The skill is designed to ingest data from external, untrusted sources such as live URLs and Figma files, creating a surface for indirect prompt injection.
- Ingestion points: The agent is instructed to use tools like
WebFetchto retrieve content from external screens and URLs provided by users during the Phase 1 Scope step. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the audited content.
- Capability inventory: The skill has access to
Bash,WebFetch,WebSearch, andReadtools, which could be leveraged if an indirect injection attack were successful. - Sanitization: There are no documented protocols for sanitizing or filtering input from the web before the agent processes it for the design audit.
Audit Metadata