Feishu Send Image

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This skill appears to do what it says—send a chosen local image through Feishu—but it uses your Feishu app secret and bot permissions to do so.

Before installing, make sure you trust the Feishu app credentials being used, confirm the bot has only the needed permissions, and verify the image path and recipient each time you send an image. The provided code is simple and purpose-aligned, but the metadata should better advertise its curl/python3 requirements and credential use.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

#
ASI02: Tool Misuse and Exploitation
Low
What this means

If the wrong recipient or image path is supplied, the bot may send the image to the wrong Feishu user or group.

Why it was flagged

The skill intentionally uses direct Feishu API calls instead of the built-in message tool. This is disclosed and purpose-aligned, but it means the script can send bot messages to any supplied Feishu receive_id.

Skill content
This skill bypasses that limitation by calling Feishu Bot API directly.
Recommendation

Use only verified recipient IDs and image paths, and consider adding a confirmation step before sending to group chats or external recipients.

#
ASI03: Identity and Privilege Abuse
Medium
What this means

Anyone able to use the app secret with the required Feishu permissions could send bot messages and upload images through that Feishu app.

Why it was flagged

The skill relies on a local Feishu app secret to obtain a tenant access token and act as the Feishu bot. This is expected for the stated function, but it is sensitive account authority.

Skill content
Read `~/.openclaw/openclaw.json` and extract:
- `channels.feishu.accounts.default.appId`
- `channels.feishu.accounts.default.appSecret`
Recommendation

Keep the app secret protected, grant only the needed Feishu permissions, and avoid exposing secrets in logs, transcripts, or shared command histories.

#
ASI07: Insecure Inter-Agent Communication
Low
What this means

The chosen image becomes available to Feishu for delivery as a chat image, so sensitive screenshots or charts could be shared if selected by mistake.

Why it was flagged

The script uploads the selected local image file to Feishu's image API. This external data flow is disclosed and central to the purpose, but users should understand the file leaves the local machine.

Skill content
curl -s -X POST 'https://open.feishu.cn/open-apis/im/v1/images' ... -F "image=@$IMAGE_PATH"
Recommendation

Confirm that the selected image is appropriate to upload and send, and avoid using broad or ambiguous file paths.

#
ASI04: Agentic Supply Chain Vulnerabilities
Low
What this means

The skill may fail or behave differently on systems without curl and python3, even though the registry requirements do not advertise those prerequisites.

Why it was flagged

The README declares runtime dependencies, while the registry metadata says there are no required binaries and there is no install spec. This may make the runtime requirements less visible at install time.

Skill content
- 系统已安装 `curl` 和 `python3`
Recommendation

Declare curl and python3 in the skill metadata or installation requirements so users can review prerequisites before installing.