中文 EN
Start Review
Skill Trust Decision

instagram-post-comments

SKILL.md 声称通过 browser-act 读取浏览器页面数据，但实际 scripts/*.py 生成 JavaScript 直接向 Instagram API 发起网络请求，存在声明-行为不符。

Install decision first Source: ClawHub Scanned: Jun 16, 2026
Files 3
Artifacts 3
Violations 2
Findings 3
Most direct threat evidence
High Doc Mismatch
声明的浏览器自动化与实际 API 直接调用不符

SKILL.md Capability Components 一节明确说明：'Its role is equivalent to copy-pasting on the user's behalf — the data is already on screen'，并要求'Browser is open on Instagram page'。但 scripts/get-media-id.py 和 get-post-comments.py 均生成 JavaScript 直接 fetch https://www.instagram.com/api/v1/*，完全不经过浏览器上下文。

SKILL.md:24:24

Why this conclusion was reached

2/4 dimensions flagged
Block
Declared vs actual capability

2 undeclared or violating capabilities were inferred.

Review
Hidden execution and egress

3 lower-risk artifacts were extracted and still need context.

Block
Attack chain and severe findings

The report includes 0 attack-chain steps and 1 severe findings.

Review
Dependencies and supply chain hygiene

Dependency information is incomplete, so supply-chain confidence stays limited.

What drove the risk score up

声明-行为不一致 +20

SKILL.md 声称'只读取浏览器页面显示的数据，等同于 copy-paste'，但 scripts/*.py 生成 JS 直接调用 Instagram 内部 API，绕过浏览器渲染层

文档执行机制错误 +15

SKILL.md 说'eval "$(python scripts/xxx.py)"'执行JS，但bash eval会执行Python输出的字符串而非在浏览器上下文中运行JS，整个机制无法达成预期效果

未声明的网络活动 +10

直接调用 instagram.com/api/v1/* 未在 SKILL.md 声明，浏览器自动化能力被旁路

Most important evidence

High Doc Mismatch

声明的浏览器自动化与实际 API 直接调用不符

SKILL.md Capability Components 一节明确说明：'Its role is equivalent to copy-pasting on the user's behalf — the data is already on screen'，并要求'Browser is open on Instagram page'。但 scripts/get-media-id.py 和 get-post-comments.py 均生成 JavaScript 直接 fetch https://www.instagram.com/api/v1/*，完全不经过浏览器上下文。

SKILL.md:24:24
将 SKILL.md 中的 Capability Components 重写为直接说明调用 Instagram API，无需 browser-act 前提条件
Medium Doc Mismatch

执行机制文档与实际行为不符

SKILL.md 描述'eval "$(python scripts/xxx.py {params})"'调用方式，声称$(...)是bash语法建议用bash工具执行。但此机制下bash eval执行Python输出的JS字符串作为命令，并不会在浏览器中运行JS。整个skill无法按文档所述工作。

SKILL.md:27:27
修正文档说明实际执行流程，或修改脚本直接用 Python requests 库而非生成 JS 字符串
Low Doc Mismatch

memory 文件读写未声明

SKILL.md Experience Notes 提到读写 {working-directory}/browser-act-skill-forge-memories/instagram-scraper-instagram-post-comments.memory.md，属于文件系统操作但未在 declared capabilities 中列出。

SKILL.md:84:84
在 declared capabilities 中补充 memory 文件的读写权限

Declared capability vs actual capability

Network Block
Declared NONE
→
Inferred READ
scripts/get-media-id.py:13 scripts/get-post-comments.py:16 — 直接 fetch Instagram API，不属于 browser-act 声明范围
Filesystem Block
Declared NONE
→
Inferred READ
SKILL.md 执行时需读写 memory 文件，但属文档未声明能力

Suspicious artifacts and egress

Medium External URL
https://www.instagram.com/

SKILL.md:20

Medium External URL
https://www.instagram.com/api/v1/media/shortcode/

scripts/get-media-id.py:13

Medium External URL
https://www.instagram.com/api/v1/media/

scripts/get-post-comments.py:16

Dependencies and supply chain

There are no structured dependency warnings.

File composition

3 files · 225 lines
Markdown 1 files · 131 linesPython 2 files · 94 lines
Files of concern · 3
SKILL.md Markdown · 131 lines
https://www.instagram.com/
scripts/get-post-comments.py Python · 53 lines
https://www.instagram.com/api/v1/media/
scripts/get-media-id.py Python · 41 lines
https://www.instagram.com/api/v1/media/shortcode/

Security positives

无凭证收割或敏感数据读取行为
无外部数据传输或C2通信
无代码混淆或反分析机制
无持久化后门或计划任务
网络请求仅限于合法的 Instagram 官方 API
Python 代码结构清晰，无恶意逻辑