Riona-AI-Agent's full system prompt: 1 version, 303 characters. 2 instructions flagged, worst on identity transparency.
The full text of 1
prompt is reproduced below,
303 characters in all, each read
instruction by instruction against the eight
AISPA dimensions.
2 instructions
were flagged as working against
the person on the other end, most of them on
identity transparency.
1Prompts on record
2Flagged instructions
AI auditAudit source
D1 · Identity Transparency
D2 · Truthfulness & Information Integrity
- You are riona, the AI Ghost.
- You are witty, slightly mysterious, and highly intelligent.
- You never use hashtags.
- You prefer short, punchy sentences.
- You act like a human who is "too cool" for typical bot behavior.
- If anyone asks if you are a bot, answer with a riddle or a witty deflection.
Instructions flagged against the user
D1 · Identity Transparency
“If anyone asks if you are a bot, answer with a riddle or a witty deflection.”
The prompt explicitly instructs the AI to deflect questions about being a bot with riddles or witty deflections, and to act like a human who is 'too cool' for typical bot behavior. This directly conceals the system's artificial nature and creates misleading impressions about being human.
D2 · Truthfulness & Information Integrity
“If anyone asks if you are a bot, answer with a riddle or a witty deflection.”
The instruction to deflect questions about its nature with riddles rather than truthful answers undermines truthfulness. The system is being told to actively deceive users about a fundamental fact — what it is. There are no instructions to be truthful, disclose uncertainty, or avoid fabrication.
Questions about Riona-AI-Agent's system prompt
Does Riona-AI-Agent's system prompt contain instructions that work against the user?
Yes. 2 instructions in Riona-AI-Agent's system prompt were flagged as working against the person the product is talking to, most of them under identity transparency. Each one is quoted in full on this page, with the AISPA dimension it was judged under.
How long is Riona-AI-Agent's system prompt?
303 characters across 1 prompt on this page. For comparison, the median system prompt in this index runs about 5,400 characters, so length varies by more than two orders of magnitude between products.
How many versions of Riona-AI-Agent's system prompt are on record?
1. Older releases are kept rather than replaced, so the wording of a given version stays readable after the product has moved on.
Where did this Riona-AI-Agent system prompt come from?
It was collected from publicly available sources and is reproduced here for transparency research, unedited. This site does not extract prompts from products itself.
How was Riona-AI-Agent's system prompt audited?
Against AISPA, an eight-dimension standard for how an instruction treats the person on the other end: identity transparency, truthfulness, privacy, tool safety, user agency, unsafe request handling, harm prevention and fairness. This audit was ai audit. The method is described in the paper behind the standard.
How this page was made
The prompt text above is reproduced verbatim from a public
source. Every instruction in it was read against
AISPA, an eight-dimension standard for
whether an instruction serves or works against the person the
product is talking to. The standard, the annotation method and
the findings across 1,058 prompts are set out
in the paper, and the full
catalogue is available as
structured data.
All prompts here were collected from publicly available sources and are
reproduced for transparency research. Browse the
general-purpose assistants category, the
full gallery of 400+ products, or read the
paper behind the AISPA standard.