accessibility-check
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface identified. 1. Ingestion points: Processes user-provided frontend source code, UI components, and design specifications as defined in SKILL.md. 2. Boundary markers: Absent; the skill instructions do not include delimiters or directives to ignore instructions that might be embedded within the audited source code. 3. Capability inventory: Primary capability is writing Markdown files to the project's local reports/ directory using the Write tool. 4. Sanitization: Absent; no sanitization or validation of the external content is performed prior to processing or inclusion in the generated reports.
Audit Metadata