blog-post
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary function is the generation of static HTML and CSS content for articles. It does not perform network requests, file system modifications (outside of artifact generation), or execution of arbitrary code.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions specify reading an external
DESIGN.mdfile to guide the generation process. This constitutes an ingestion point for potentially untrusted data. However, since the skill only produces static HTML artifacts and lacks capabilities such as command execution or network exfiltration, the risk surface is minimal. - Ingestion points: Reads
DESIGN.mdfor design tokens and typography hierarchy. - Boundary markers: Absent; there are no specific delimiters or instructions to ignore embedded commands in the design file.
- Capability inventory: None; the skill does not use subprocesses, file writes, or network tools. It only emits a text artifact.
- Sanitization: Not explicitly defined in the workflow.
Audit Metadata