eli5
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directly interpolates user-provided content into its instruction prompt without isolation, creating a vulnerability to indirect prompt injection.
- Ingestion points: User input enters the prompt via the
$ARGUMENTSvariable inSKILL.md. - Boundary markers: The skill fails to use delimiters (such as XML tags, triple backticks, or quotes) to distinguish the user's topic from the agent's instructions.
- Capability inventory: The skill instructs the agent to generate HTML artifacts, which could be abused if the input contains malicious instructions.
- Sanitization: There is no evidence of input validation or instructions telling the agent to treat the input strictly as data.
Audit Metadata