CD story-video
当用户提到以下内容时触发此技能： 把故事做成视频、生成视频、故事视频、AI视频制作、文生视频、图生视频、剧本转视频、分镜生成、分镜头、导演分镜、编剧分析、故事分镜、需要分镜、给视频分镜、拍成视频、拍成分镜、generate video、story to video、video generation、video script、screenplay analysis、shot breakdown、scene breakdown、film directing、编剧、导演、分镜、分镜头、给个分镜 这是一个AI视频制作流水线，覆盖从故事文本到分镜再到视频生成的全流程： 从分析故事结构、提炼主题，到设计人物对白、构建叙事节奏； 从编写分镜脚本、设计镜头语言，到生成视觉描述词； 从文本到图片、图片到视频的生成，再到ffmpeg合并输出最终成片。
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 6
-
high Obfuscation
uni-zero-widthreferences/minimax-api/models-intro.txt:3Zero-width / invisible characters (possible hidden text) (7 occurrences)在此页面旗舰模型模型概览语音模型视频模型图片模型音乐模型推荐阅读开始使用概览复制页面MiniMax 模型体系涵盖文本、语音、视频、图像与音乐五大方向。旗舰模型性能领先，助力开发者高效构建智能应用。复制页面␀旗舰模型 MiniMax M2.7开启模型的自我迭代Music2.6以声传情：翻唱入心，器乐入魂MiniMax H…
Medium and low: 5
-
medium Exfiltration
net-redirectable-api-keyscripts/full_pipeline_v2.py:15Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Exfiltration
net-redirectable-api-keyscripts/full_pipeline.py:15Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Exfiltration
net-redirectable-api-keyscripts/generate_shot_images.py:26Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Exfiltration
net-redirectable-api-keyscripts/generate_shot_videos.py:19Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Broad scope
meta-requests-env-secretSKILL.md:1Skill asks the runtime to inject credential env vars into its sandbox: MINIMAX_API_KEY — verify each one is needed for the stated purposerequired_environment_variables: MINIMAX_API_KEY
Files scanned: 28. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "trigger" - note
frontmatter-keyunknown frontmatter key "required_environment_variables" - note
frontmatter-keyunknown frontmatter key "optional_environment_variables"
Process rating: all ten parameters 49/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (story-video) differs from the folder (story-video-skill)
- 100Tools and files. No external tools needed
- 100Steps. 28 steps
- 100Execution cost. Instruction body is 828 tokens
- 100Running it twice. No mutating operations
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -32 of 7 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 370: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 28 items
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.