eli5
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates user-provided content ($ARGUMENTS) directly into a prompt that instructs the agent to generate an HTML artifact.
- Ingestion points: User-supplied input via
$ARGUMENTSinSKILL.mdis interpolated directly into the prompt. - Boundary markers: The skill lacks delimiters or explicit instructions to ignore embedded commands within the
$ARGUMENTSstring. - Capability inventory: The skill's primary capability is generating a rendered HTML artifact based on the input.
- Sanitization: There are no sanitization or filtering instructions to prevent the agent from executing instructions hidden within the user-provided topic.
Audit Metadata