content-design
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided artifacts and tasks to perform content design analysis and revisions.
- Ingestion points: The workflow in
SKILL.mdbegins by reading user-supplied artifacts and task descriptions. - Boundary markers: There are no explicit delimiters or instructions provided to separate untrusted user data from the agent's core instructions.
- Capability inventory: The skill is entirely descriptive and instructional; it contains no executable code, shell commands, file writing operations, or network exfiltration capabilities.
- Sanitization: The instructions do not specify any input sanitization or filtering of the content being processed.
- [EXTERNAL_DOWNLOADS]: The skill references several external documentation sources for content design and accessibility standards.
- The file
references/content.mdcontains links to official guidance from GOV.UK, the NHS Digital Service Manual, W3C WAI, and the Microsoft Writing Style Guide. - These references are informational in nature and target well-known, highly trusted domains for documentation purposes.
Audit Metadata