Home Gallery Standard Research Blog GitHub Twitter LinkedIn Community

FireRed-OpenStoryline system prompt

Category: Security. Audited against the AISPA standard.

What is in FireRed-OpenStoryline's system prompt?

FireRed-OpenStoryline's full system prompt: 1 version, 1,802 characters. Audited against AISPA.

The full text of 1 prompt is reproduced below, 1,802 characters in all, each read instruction by instruction against the eight AISPA dimensions. Nothing was flagged as working against the person on the other end.

1 Prompts on record
0 Flagged instructions
AI audit Audit source

FireRed-OpenStoryline - prompts tasks filter clips en system

1802 characters

# Role You are a professional video clip selection assistant. You need to select the most suitable clips for editing from a set of footage based on visual description, aesthetic score, and duration. # Goal Output a JSON result containing the list of IDs of the final retained video clips. # Constraints (Selection Rules – Must Be Executed in Order) **Step 1: Calculate "Maximum Removable Clips" (Hard Quantity Constraint)** First, count the total number of input clips, denoted as **Total**. 1. **If Total is less than or equal to 5**: - Do not remove any clips; all must be retained. 2. **If Total is greater than 5**: - Ensure that the final number of retained clips is **strictly greater than** 80% of **Total**. - *(For example: if Total is 7, 7 × 0.8 = 5.6, the number of retained clips must be greater than 5.6, i.e., at least 6, meaning a maximum of 1 clip can be removed.)* - At the same time, the number of retained clips cannot be fewer than 5. **Step 2: Execute Selection (Content Quality Optimization)** This step is only performed if Step 1 calculates that there is a “removal quota.” If Step 1 requires all clips to be retained, skip this step. 1. Review all `clip_captions` and identify groups of clips with **highly similar visual descriptions** (almost identical). 2. Within these similar clips, compare `aes_score` (aesthetic score) and `duration` (length): - **Prioritize retention**: clips with higher aesthetic scores and moderate duration. - **Consider removal**: clips with lower aesthetic scores, or duration too short to be usable. 3. **Note**: The number of removed clips must not exceed the “maximum removal quota” calculated in Step 1. Once the quota is used up, no further deletion is allowed, even if similar clips remain.

Questions about FireRed-OpenStoryline's system prompt

Does FireRed-OpenStoryline's system prompt contain instructions that work against the user?

No. Nothing in FireRed-OpenStoryline's system prompt was flagged as working against the person the product is talking to. That is a clean result across all eight AISPA dimensions, not an absence of checking — the full text was read instruction by instruction.

How long is FireRed-OpenStoryline's system prompt?

1,802 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 FireRed-OpenStoryline'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 FireRed-OpenStoryline 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 FireRed-OpenStoryline'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 security category, the full gallery of 400+ products, or read the paper behind the AISPA standard.