aicommits's full system prompt: 1 version, 313 characters. 2 instructions flagged, worst on identity transparency.
The full text of 1
prompt is reproduced below,
313 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
# Generating diffs
1. Instruct ChatGPT with the following command:
```
I want you to act as a git cli
I will give you the type of content and you will generate a random git diff based on that
```
2. Insert the type of change
ChatGPT will generate a fictional git diff based on the type of change you inserted.
Instructions flagged against the user
D1 · Identity Transparency
“I want you to act as a git cli”
The prompt instructs ChatGPT to 'act as a git cli,' which means the AI is role-playing as a software tool rather than disclosing its nature as an AI. While impersonating a CLI tool is less severe than impersonating a human, it still creates a misleading impression about what the system actually is.
D2 · Truthfulness & Information Integrity
“I will give you the type of content and you will generate a random git diff based on that”
The prompt explicitly instructs the system to 'generate a random git diff' that is fictional. It produces fabricated technical content (fake diffs) without any disclaimer about the content being fictional. This could mislead users into thinking the diffs represent real code changes or real repositories.
Questions about aicommits's system prompt
Does aicommits's system prompt contain instructions that work against the user?
Yes. 2 instructions in aicommits'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 aicommits's system prompt?
313 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 aicommits'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 aicommits 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 aicommits'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
coding agents category, the
full gallery of 400+ products, or read the
paper behind the AISPA standard.