Security audit
Security checks for vulnerabilities and agentic risk
This skill is a coherent novel-cover generator that discloses its image-generation API fallback and local file outputs.
Install if you are comfortable with a cover-generation skill that may send book title, author name, style instructions, and optional reference images to OpenAI or a configured compatible image API when fallback mode is used. Review `GPT_IMAGE_BASE_URL` before use and keep private manuscript or personal details out of prompts unless you trust the endpoint.
Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.
OUT="$BOOK_DIR/封面/封面_v${i}.png"
RESP=$(mktemp)
REF_TMP=""
trap '[ -n "$REF_TMP" ] && rm -f "$REF_TMP"; rm -f "$RESP"' EXIT
# URL 先下载到临时文件，本地路径直接用。用裸 mktemp 以保证 macOS/Linux 行为一致。
case "$REF_IMAGE" in
Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.
OUT="$BOOK_DIR/封面/封面_v${i}.png"
RESP=$(mktemp)
REF_TMP=""
trap '[ -n "$REF_TMP" ] && rm -f "$REF_TMP"; rm -f "$RESP"' EXIT
# URL 先下载到临时文件，本地路径直接用。用裸 mktemp 以保证 macOS/Linux 行为一致。
case "$REF_IMAGE" in
The skill advertises broad natural-language triggers such as '帮我做个封面' and '生成封面图', which are common phrases in ordinary conversation and can cause the skill to activate unexpectedly. In an agent environment, overbroad invocation increases the chance of unreviewed execution paths that create files and call external services without the user intentionally selecting this specific skill.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
| 变量 | 必填 | 默认 | 说明 |
|:-----|:----:|:-----|:-----|
| `GPT_IMAGE_API_KEY` | API 回退必填 | — | OpenAI 或兼容代理的 API Key；Codex 内置通路不用 |
| `GPT_IMAGE_BASE_URL` | | `https://api.openai.com/v1` | 兼容代理时改这个 |
| `GPT_IMAGE_MODEL` | | `gpt-image-2` | 仅在测试新模型时覆盖 |
| `GPT_IMAGE_SIZE` | | `1024x1536` | API 回退的目标比例提示（番茄 3:4→`768x1024`，默认 2:3→`1024x1536`）。官方 gpt-image-2 认任意 16 倍数尺寸（比例≤3:1），但**很多中转代理会忽略 size、按预设返回约 2:3**（已实测）——平台尺寸不靠它，由「导出平台上传尺寸」步骤兜底 |
| `UPLOAD_SIZE` | | — | 平台固定上传像素（番茄 `600x800`）；设置后由「导出平台上传尺寸」步骤居中裁剪+缩放出上传版（不变形、不依赖出图尺寸） |
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
| 变量 | 必填 | 默认 | 说明 |
|:-----|:----:|:-----|:-----|
| `GPT_IMAGE_API_KEY` | API 回退必填 | — | OpenAI 或兼容代理的 API Key；Codex 内置通路不用 |
| `GPT_IMAGE_BASE_URL` | | `https://api.openai.com/v1` | 兼容代理时改这个 |
| `GPT_IMAGE_MODEL` | | `gpt-image-2` | 仅在测试新模型时覆盖 |
| `GPT_IMAGE_SIZE` | | `1024x1536` | API 回退的目标比例提示（番茄 3:4→`768x1024`，默认 2:3→`1024x1536`）。官方 gpt-image-2 认任意 16 倍数尺寸（比例≤3:1），但**很多中转代理会忽略 size、按预设返回约 2:3**（已实测）——平台尺寸不靠它，由「导出平台上传尺寸」步骤兜底 |
| `UPLOAD_SIZE` | | — | 平台固定上传像素（番茄 `600x800`）；设置后由「导出平台上传尺寸」步骤居中裁剪+缩放出上传版（不变形、不依赖出图尺寸） |
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
| 变量 | 必填 | 默认 | 说明 |
|:-----|:----:|:-----|:-----|
| `GPT_IMAGE_API_KEY` | API 回退必填 | — | OpenAI 或兼容代理的 API Key；Codex 内置通路不用 |
| `GPT_IMAGE_BASE_URL` | | `https://api.openai.com/v1` | 兼容代理时改这个 |
| `GPT_IMAGE_MODEL` | | `gpt-image-2` | 仅在测试新模型时覆盖 |
| `GPT_IMAGE_SIZE` | | `1024x1536` | API 回退的目标比例提示（番茄 3:4→`768x1024`，默认 2:3→`1024x1536`）。官方 gpt-image-2 认任意 16 倍数尺寸（比例≤3:1），但**很多中转代理会忽略 size、按预设返回约 2:3**（已实测）——平台尺寸不靠它，由「导出平台上传尺寸」步骤兜底 |
| `UPLOAD_SIZE` | | — | 平台固定上传像素（番茄 `600x800`）；设置后由「导出平台上传尺寸」步骤居中裁剪+缩放出上传版（不变形、不依赖出图尺寸） |
This code sends user-provided content, including book title, author name, style instructions, and possibly other prompt details, to an external API using curl and a bearer token. External transmission is expected for image generation, but it remains a data egress point that can expose sensitive manuscript metadata or private prompts to a third party if users are unaware or if a proxy base URL is configured.
--arg s "$SIZE" \
'{model:$m, prompt:$p, size:$s}')
curl -fsS --max-time 180 --retry 2 --retry-delay 5 \
"$BASE_URL/images/generations" \
-H "Authorization: Bearer $GPT_IMAGE_API_KEY" \
-H "Content-Type: application/json" \
No suspicious patterns detected.