article-to-html
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted markdown content from the conversation context or user-provided files, which creates a surface for indirect prompt injection.
- Ingestion points: Untrusted source content enters the context via the
Readtool as specified in the first step of the flow inSKILL.md. - Boundary markers: The skill does not define specific boundary markers or instructions to isolate the interpolated markdown from the surrounding HTML scaffold, relying on the model to perform the mapping safely.
- Capability inventory: Across its scripts and instructions, the skill utilizes
ReadandWritecapabilities to access source documents and create resulting HTML files on the local file system. - Sanitization: There is no evidence of sanitization, escaping, or filtering of the input markdown content before it is placed into the
template.htmlscaffold. Malicious HTML or JavaScript tags within the source document could potentially be included in the generated output file.
Audit Metadata