eli5
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input directly via the $ARGUMENTS variable.
- Ingestion points: User-supplied text provided after the /eli5 command as captured by $ARGUMENTS in SKILL.md.
- Boundary markers: The instruction set lacks delimiters (such as triple backticks or quotes) or explicit system-level instructions to treat the user input strictly as data and ignore any embedded control commands.
- Capability inventory: The skill is designed to generate HTML artifacts based on the provided topic.
- Sanitization: No validation or sanitization of the $ARGUMENTS content is implemented before it is interpolated into the final prompt.
Audit Metadata